Find the right AI for you

Search by name or tell us what you want to do
API servicesChoose how to access modelsAI modelsCapabilities, specifications, and pricingAI toolsFind useful tools by taskMCP directoryConnect tools, data, and workflowsAgent skillsFind reusable skills for AI agentsBenchmarksCompare model performanceOnline toolsConvert accounts, format JSON, estimate costs and test APIsModel timelineExplore model releasesUse casesStart with a practical task
EnterSearch · ↑↓Choose a resultEscClose
Submit中文
Project benchmark

EuroEval European languages · Test split · few-shot

EuroEval · 268 configurations with published scores. Review each metric and its test conditions separately.

Report identity & conditions

Data as of2026-10-18· Report published—. See individual records for run dates and test conditions.

Leaderboard updated

  • Mean rank scores cover the European generative datasets; lower is better. Overall and language-specific scores are separate. Missing scores are not zero.
  • Test and validation splits, and few-shot and zero-shot prompts, have separate pages. Thinking modes and model types remain part of each run’s identity; matching names do not merge configurations.
  • The ± value is the half-width of a 95% bootstrap confidence interval. Charts sort by point estimate, but small differences with overlapping intervals do not establish superiority.
  • Hugging Face models are linked only when the official URL exactly matches the catalog identifier. Short names, API prefixes and thinking modes do not establish an exact version.
  • Model metadata, European values and hallucination rates are outside this page’s ranking metrics. This leaderboard does not measure general ability across all tasks or languages.
  • The EuroEval results repository and framework use the MIT License, Copyright © Dan Saattrup Smart and Alexandra Instituttet A/S. Full terms: /licenses/euroeval.txt.
  • Leaderboard updated: 2026-10-10 14:26:33 CET. This is not a model release date or an individual test date.
  • This page covers Test split with few-shot prompts. Model types remain attached to individual records. Per-run test dates, framework versions and a common sample count are not stated and are not inferred.
Read the original report ↗

Compare metrics within the same report. Each chart explains its direction and scope.
Error bars show 95% confidence intervals.See the details for full values and run conditions.

Mean European-language rank score

Mean rank score across the European generative tasks; lower is better. ± is the half-width of a 95% bootstrap confidence interval. Scores are not ranked across different datasets.: showing 8 of 43 records with values. See details for configurations and dates.

Chart data · 8 entries
NameRank score
mistralai/Mistral-Small-3.2-24B-Instruct-25061.84 ± 0.07 (95% CI)
mistralai/Mistral-Small-3.1-24B-Instruct-25031.85 ± 0.06 (95% CI)
Qwen/Qwen3-32B#no-thinking1.9 ± 0.06 (95% CI)
google/gemma-3-27b-pt1.92 ± 0.07 (95% CI)
mistralai/Mistral-Small-3.1-24B-Base-25031.93 ± 0.06 (95% CI)
deepcogito/cogito-v1-preview-qwen-32B1.94 ± 0.08 (95% CI)
Qwen/Qwen3-14B#no-thinking2.01 ± 0.07 (95% CI)
google/gemma-3-12b-it2.06 ± 0.07 (95% CI)

Albanian mean rank score

Mean rank score for Albanian; lower is better. ± is the half-width of a 95% bootstrap confidence interval. Scores are not ranked across different datasets.: showing 8 of 69 records with values. See details for configurations and dates.

Chart data · 8 entries
NameRank score
mistralai/Mistral-Small-3.1-24B-Instruct-25031.79 ± 0.03 (95% CI)
mistralai/Mistral-Small-3.2-24B-Instruct-25061.8 ± 0.03 (95% CI)
google/gemma-3-27b-it1.81 ± 0.04 (95% CI)
Qwen/Qwen3-32B#no-thinking1.84 ± 0.03 (95% CI)
google/gemma-3-27b-pt1.98 ± 0.05 (95% CI)
Qwen/Qwen3-14B#no-thinking1.98 ± 0.05 (95% CI)
deepcogito/cogito-v2-preview-llama-70B2.02 ± 0.04 (95% CI)
mistralai/Mistral-Small-3.1-24B-Base-25032.05 ± 0.04 (95% CI)

Full results & model versions

268 / 469configurations have published scores in this scope. Scored configurations are listed; missing values remain “Not provided.” Different run configurations of the same model are listed separately.

allenai/Olmo-3-7B-Think →

Linked to an exact version in our directory

Test split · few-shot · Reasoning model

Mean European-language rank score
Not provided
Bulgarian mean rank score
3 ± 0.02（95% CI） 排名分
Croatian mean rank score
2.72 ± 0.03（95% CI） 排名分
Faroese mean rank score
3.96 ± 0.06（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Catalan mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
3.08 ± 0.04（95% CI） 排名分
Slovene mean rank score
3.08 ± 0.04（95% CI） 排名分
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

facebook/MobileLLM-R1-140M

Model reported by the benchmark

Test split · few-shot · Reasoning model

Mean European-language rank score
Not provided
Faroese mean rank score
4.84 ± 0.03（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

allenai/OLMo-2-1124-7B

Model reported by the benchmark

Test split · few-shot · Base generative

Mean European-language rank score
Not provided
Faroese mean rank score
3.88 ± 0.05（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

deepseek-ai/DeepSeek-R1-Distill-Qwen-32B →

Linked to an exact version in our directory

Test split · few-shot · Reasoning model

Mean European-language rank score
Not provided
Faroese mean rank score
3.91 ± 0.06（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

utter-project/EuroVLM-9B-Preview

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
Not provided
Faroese mean rank score
4.86 ± 0（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

Qwen/Qwen3-1.7B#no-thinking

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
2.77 ± 0.07（95% CI） 排名分
Albanian mean rank score
2.75 ± 0.04（95% CI） 排名分
Belarusian mean rank score
2.98 ± 0.05（95% CI） 排名分
Bosnian mean rank score
1.87 ± 0.04（95% CI） 排名分
More metrics
Bulgarian mean rank score
3.2 ± 0.02（95% CI） 排名分
Catalan mean rank score
2.49 ± 0.03（95% CI） 排名分
Croatian mean rank score
2.87 ± 0.04（95% CI） 排名分
Czech mean rank score
2.62 ± 0.03（95% CI） 排名分
Danish mean rank score
2.94 ± 0.04（95% CI） 排名分
Dutch mean rank score
2.68 ± 0.13（95% CI） 排名分
English mean rank score
2.14 ± 0.03（95% CI） 排名分
Estonian mean rank score
2.92 ± 0.03（95% CI） 排名分
Faroese mean rank score
4.04 ± 0.04（95% CI） 排名分
Finnish mean rank score
2.85 ± 0.03（95% CI） 排名分
French mean rank score
2.44 ± 0.14（95% CI） 排名分
German mean rank score
2.74 ± 0.18（95% CI） 排名分
Greek mean rank score
2.95 ± 0.04（95% CI） 排名分
Hungarian mean rank score
2.81 ± 0.02（95% CI） 排名分
Icelandic mean rank score
3.37 ± 0.04（95% CI） 排名分
Italian mean rank score
2.69 ± 0.17（95% CI） 排名分
Latvian mean rank score
2.68 ± 0.04（95% CI） 排名分
Lithuanian mean rank score
2.75 ± 0.04（95% CI） 排名分
Luxembourgish mean rank score
2.88 ± 0.22（95% CI） 排名分
Norwegian mean rank score
2.7 ± 0.06（95% CI） 排名分
Polish mean rank score
2.92 ± 0.03（95% CI） 排名分
Portuguese mean rank score
2.57 ± 0.04（95% CI） 排名分
Romanian mean rank score
2.56 ± 0.02（95% CI） 排名分
Serbian mean rank score
2.6 ± 0.02（95% CI） 排名分
Slovak mean rank score
3.07 ± 0.03（95% CI） 排名分
Slovene mean rank score
3.17 ± 0.03（95% CI） 排名分
Spanish mean rank score
2.72 ± 0.13（95% CI） 排名分
Swedish mean rank score
2.75 ± 0.12（95% CI） 排名分
Ukrainian mean rank score
2.67 ± 0.02（95% CI） 排名分

TildeAI/TildeOpen-30b#slow-tokenizer

Model reported by the benchmark

Test split · few-shot · Base generative

Mean European-language rank score
Not provided
Faroese mean rank score
3.77 ± 0.06（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

CohereForAI/c4ai-command-r7b-12-2024

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
Not provided
Faroese mean rank score
3.54 ± 0.05（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

LiquidAI/LFM2-700M →

Linked to an exact version in our directory

Test split · few-shot · Instruction-tuned

Mean European-language rank score
3.8 ± 0.05（95% CI） 排名分
Albanian mean rank score
3.7 ± 0.05（95% CI） 排名分
Belarusian mean rank score
3.93 ± 0.03（95% CI） 排名分
Bosnian mean rank score
3.32 ± 0.04（95% CI） 排名分
More metrics
Bulgarian mean rank score
4.13 ± 0.02（95% CI） 排名分
Catalan mean rank score
3.51 ± 0.03（95% CI） 排名分
Croatian mean rank score
4.12 ± 0.03（95% CI） 排名分
Czech mean rank score
3.88 ± 0.03（95% CI） 排名分
Danish mean rank score
3.8 ± 0.03（95% CI） 排名分
Dutch mean rank score
3.83 ± 0.11（95% CI） 排名分
English mean rank score
3.24 ± 0.02（95% CI） 排名分
Estonian mean rank score
3.91 ± 0.02（95% CI） 排名分
Faroese mean rank score
4.53 ± 0.05（95% CI） 排名分
Finnish mean rank score
3.96 ± 0.03（95% CI） 排名分
French mean rank score
3.33 ± 0.11（95% CI） 排名分
German mean rank score
3.77 ± 0.1（95% CI） 排名分
Greek mean rank score
4.01 ± 0.06（95% CI） 排名分
Hungarian mean rank score
3.87 ± 0.02（95% CI） 排名分
Icelandic mean rank score
3.98 ± 0.05（95% CI） 排名分
Italian mean rank score
3.63 ± 0.14（95% CI） 排名分
Latvian mean rank score
3.61 ± 0.05（95% CI） 排名分
Lithuanian mean rank score
3.75 ± 0.02（95% CI） 排名分
Luxembourgish mean rank score
3.83 ± 0.1（95% CI） 排名分
Norwegian mean rank score
3.68 ± 0.05（95% CI） 排名分
Polish mean rank score
3.88 ± 0.03（95% CI） 排名分
Portuguese mean rank score
3.34 ± 0.03（95% CI） 排名分
Romanian mean rank score
3.64 ± 0.03（95% CI） 排名分
Serbian mean rank score
3.66 ± 0.02（95% CI） 排名分
Slovak mean rank score
4.41 ± 0.02（95% CI） 排名分
Slovene mean rank score
4.27 ± 0.03（95% CI） 排名分
Spanish mean rank score
3.52 ± 0.12（95% CI） 排名分
Swedish mean rank score
3.8 ± 0.11（95% CI） 排名分
Ukrainian mean rank score
3.95 ± 0.03（95% CI） 排名分

01-ai/Yi-1.5-34B

Model reported by the benchmark

Test split · few-shot · Base generative

Mean European-language rank score
Not provided
Faroese mean rank score
3.57 ± 0.05（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

utter-project/EuroLLM-22B-Instruct-Preview

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
Not provided
Bulgarian mean rank score
2.7 ± 0.04（95% CI） 排名分
Faroese mean rank score
3.63 ± 0.05（95% CI） 排名分
Slovak mean rank score
2.36 ± 0.03（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovene mean rank score
2.47 ± 0.03（95% CI） 排名分
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

deepcogito/cogito-v1-preview-qwen-14B

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
2.15 ± 0.07（95% CI） 排名分
Albanian mean rank score
2.43 ± 0.05（95% CI） 排名分
Belarusian mean rank score
2.23 ± 0.04（95% CI） 排名分
Bosnian mean rank score
2.03 ± 0.02（95% CI） 排名分
More metrics
Bulgarian mean rank score
2.72 ± 0.02（95% CI） 排名分
Catalan mean rank score
2.13 ± 0.02（95% CI） 排名分
Croatian mean rank score
2.48 ± 0.04（95% CI） 排名分
Czech mean rank score
1.83 ± 0.02（95% CI） 排名分
Danish mean rank score
2.02 ± 0.03（95% CI） 排名分
Dutch mean rank score
2.12 ± 0.17（95% CI） 排名分
English mean rank score
1.5 ± 0.01（95% CI） 排名分
Estonian mean rank score
2.35 ± 0.02（95% CI） 排名分
Faroese mean rank score
3.04 ± 0.04（95% CI） 排名分
Finnish mean rank score
2.18 ± 0.02（95% CI） 排名分
French mean rank score
1.86 ± 0.15（95% CI） 排名分
German mean rank score
2.07 ± 0.15（95% CI） 排名分
Greek mean rank score
2.61 ± 0.02（95% CI） 排名分
Hungarian mean rank score
2.36 ± 0.02（95% CI） 排名分
Icelandic mean rank score
2.52 ± 0.03（95% CI） 排名分
Italian mean rank score
2.08 ± 0.19（95% CI） 排名分
Latvian mean rank score
1.88 ± 0.03（95% CI） 排名分
Lithuanian mean rank score
2.1 ± 0.04（95% CI） 排名分
Luxembourgish mean rank score
2.12 ± 0.07（95% CI） 排名分
Norwegian mean rank score
1.84 ± 0.09（95% CI） 排名分
Polish mean rank score
2.19 ± 0.02（95% CI） 排名分
Portuguese mean rank score
1.93 ± 0.05（95% CI） 排名分
Romanian mean rank score
2.16 ± 0.02（95% CI） 排名分
Serbian mean rank score
1.9 ± 0.03（95% CI） 排名分
Slovak mean rank score
2.05 ± 0.02（95% CI） 排名分
Slovene mean rank score
2.58 ± 0.03（95% CI） 排名分
Spanish mean rank score
1.95 ± 0.13（95% CI） 排名分
Swedish mean rank score
2 ± 0.14（95% CI） 排名分
Ukrainian mean rank score
1.92 ± 0.03（95% CI） 排名分

infly/OpenCoder-1.5B-Base

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
Not provided
Faroese mean rank score
4.72 ± 0.06（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

ai21labs/Jamba-v0.1 →

Linked to an exact version in our directory

Test split · few-shot · Base generative

Mean European-language rank score
Not provided
Faroese mean rank score
3.61 ± 0.08（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Model reported by the benchmark

Test split · few-shot · Reasoning model

Mean European-language rank score
Not provided
Faroese mean rank score
4.34 ± 0.05（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided

utter-project/EuroLLM-9B

Model reported by the benchmark

Test split · few-shot · Base generative

Mean European-language rank score
Not provided
Albanian mean rank score
3.33 ± 0.06（95% CI） 排名分
Belarusian mean rank score
2.9 ± 0.04（95% CI） 排名分
Bosnian mean rank score
2.19 ± 0.05（95% CI） 排名分
More metrics
Bulgarian mean rank score
2.83 ± 0.04（95% CI） 排名分
Catalan mean rank score
2.77 ± 0.06（95% CI） 排名分
Croatian mean rank score
Not provided
Czech mean rank score
2.4 ± 0.05（95% CI） 排名分
Danish mean rank score
2.64 ± 0.1（95% CI） 排名分
Dutch mean rank score
2.48 ± 0.2（95% CI） 排名分
English mean rank score
2.37 ± 0.08（95% CI） 排名分
Estonian mean rank score
2.77 ± 0.06（95% CI） 排名分
Faroese mean rank score
3.75 ± 0.05（95% CI） 排名分
Finnish mean rank score
2.56 ± 0.04（95% CI） 排名分
French mean rank score
2.53 ± 0.2（95% CI） 排名分
German mean rank score
2.56 ± 0.13（95% CI） 排名分
Greek mean rank score
2.52 ± 0.04（95% CI） 排名分
Hungarian mean rank score
2.69 ± 0.07（95% CI） 排名分
Icelandic mean rank score
3.38 ± 0.04（95% CI） 排名分
Italian mean rank score
2.86 ± 0.17（95% CI） 排名分
Latvian mean rank score
2.49 ± 0.05（95% CI） 排名分
Lithuanian mean rank score
2.59 ± 0.07（95% CI） 排名分
Luxembourgish mean rank score
2.89 ± 0.18（95% CI） 排名分
Norwegian mean rank score
2.46 ± 0.1（95% CI） 排名分
Polish mean rank score
2.84 ± 0.07（95% CI） 排名分
Portuguese mean rank score
2.76 ± 0.07（95% CI） 排名分
Romanian mean rank score
2.86 ± 0.07（95% CI） 排名分
Serbian mean rank score
2.69 ± 0.03（95% CI） 排名分
Slovak mean rank score
2.92 ± 0.05（95% CI） 排名分
Slovene mean rank score
3.04 ± 0.03（95% CI） 排名分
Spanish mean rank score
2.73 ± 0.11（95% CI） 排名分
Swedish mean rank score
2.58 ± 0.09（95% CI） 排名分
Ukrainian mean rank score
2.55 ± 0.06（95% CI） 排名分

BSC-LT/salamandra-7b-instruct

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
3.3 ± 0.06（95% CI） 排名分
Albanian mean rank score
3.52 ± 0.04（95% CI） 排名分
Belarusian mean rank score
3.33 ± 0.05（95% CI） 排名分
Bosnian mean rank score
2.75 ± 0.06（95% CI） 排名分
More metrics
Bulgarian mean rank score
3.45 ± 0.03（95% CI） 排名分
Catalan mean rank score
3.15 ± 0.03（95% CI） 排名分
Croatian mean rank score
3.35 ± 0.03（95% CI） 排名分
Czech mean rank score
3.17 ± 0.03（95% CI） 排名分
Danish mean rank score
3.29 ± 0.1（95% CI） 排名分
Dutch mean rank score
3.3 ± 0.14（95% CI） 排名分
English mean rank score
3.18 ± 0.03（95% CI） 排名分
Estonian mean rank score
3.15 ± 0.03（95% CI） 排名分
Faroese mean rank score
4.32 ± 0.04（95% CI） 排名分
Finnish mean rank score
3.29 ± 0.03（95% CI） 排名分
French mean rank score
3.41 ± 0.18（95% CI） 排名分
German mean rank score
3.44 ± 0.13（95% CI） 排名分
Greek mean rank score
3.05 ± 0.03（95% CI） 排名分
Hungarian mean rank score
3.14 ± 0.03（95% CI） 排名分
Icelandic mean rank score
3.99 ± 0.04（95% CI） 排名分
Italian mean rank score
3.55 ± 0.17（95% CI） 排名分
Latvian mean rank score
3.01 ± 0.04（95% CI） 排名分
Lithuanian mean rank score
3.17 ± 0.04（95% CI） 排名分
Luxembourgish mean rank score
3.36 ± 0.08（95% CI） 排名分
Norwegian mean rank score
3.08 ± 0.07（95% CI） 排名分
Polish mean rank score
3.28 ± 0.03（95% CI） 排名分
Portuguese mean rank score
3.28 ± 0.04（95% CI） 排名分
Romanian mean rank score
3.09 ± 0.03（95% CI） 排名分
Serbian mean rank score
2.97 ± 0.02（95% CI） 排名分
Slovak mean rank score
3.39 ± 0.04（95% CI） 排名分
Slovene mean rank score
3.61 ± 0.03（95% CI） 排名分
Spanish mean rank score
3.61 ± 0.1（95% CI） 排名分
Swedish mean rank score
3.19 ± 0.1（95% CI） 排名分
Ukrainian mean rank score
3.24 ± 0.03（95% CI） 排名分

meta-llama/Llama-3.2-1B →

Linked to an exact version in our directory

Test split · few-shot · Base generative

Mean European-language rank score
3.52 ± 0.06（95% CI） 排名分
Albanian mean rank score
3.6 ± 0.06（95% CI） 排名分
Belarusian mean rank score
3.64 ± 0.05（95% CI） 排名分
Bosnian mean rank score
2.99 ± 0.05（95% CI） 排名分
More metrics
Bulgarian mean rank score
3.7 ± 0.04（95% CI） 排名分
Catalan mean rank score
3.21 ± 0.04（95% CI） 排名分
Croatian mean rank score
3.83 ± 0.03（95% CI） 排名分
Czech mean rank score
3.37 ± 0.05（95% CI） 排名分
Danish mean rank score
3.57 ± 0.04（95% CI） 排名分
Dutch mean rank score
3.27 ± 0.1（95% CI） 排名分
English mean rank score
3.25 ± 0.04（95% CI） 排名分
Estonian mean rank score
3.73 ± 0.04（95% CI） 排名分
Faroese mean rank score
4.53 ± 0.06（95% CI） 排名分
Finnish mean rank score
3.3 ± 0.04（95% CI） 排名分
French mean rank score
3.28 ± 0.09（95% CI） 排名分
German mean rank score
3.73 ± 0.13（95% CI） 排名分
Greek mean rank score
3.49 ± 0.04（95% CI） 排名分
Hungarian mean rank score
3.5 ± 0.03（95% CI） 排名分
Icelandic mean rank score
3.85 ± 0.03（95% CI） 排名分
Italian mean rank score
3.68 ± 0.13（95% CI） 排名分
Latvian mean rank score
3.58 ± 0.06（95% CI） 排名分
Lithuanian mean rank score
3.67 ± 0.05（95% CI） 排名分
Luxembourgish mean rank score
3.75 ± 0.14（95% CI） 排名分
Norwegian mean rank score
3.54 ± 0.04（95% CI） 排名分
Polish mean rank score
3.5 ± 0.04（95% CI） 排名分
Portuguese mean rank score
3.42 ± 0.09（95% CI） 排名分
Romanian mean rank score
3.28 ± 0.07（95% CI） 排名分
Serbian mean rank score
3.37 ± 0.03（95% CI） 排名分
Slovak mean rank score
3.72 ± 0.03（95% CI） 排名分
Slovene mean rank score
3.88 ± 0.03（95% CI） 排名分
Spanish mean rank score
3.56 ± 0.09（95% CI） 排名分
Swedish mean rank score
3.27 ± 0.09（95% CI） 排名分
Ukrainian mean rank score
3.42 ± 0.05（95% CI） 排名分

Qwen/Qwen3-4B#no-thinking

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
2.38 ± 0.06（95% CI） 排名分
Albanian mean rank score
2.31 ± 0.05（95% CI） 排名分
Belarusian mean rank score
2.63 ± 0.04（95% CI） 排名分
Bosnian mean rank score
1.74 ± 0.03（95% CI） 排名分
More metrics
Bulgarian mean rank score
2.68 ± 0.02（95% CI） 排名分
Catalan mean rank score
2.15 ± 0.03（95% CI） 排名分
Croatian mean rank score
2.42 ± 0.03（95% CI） 排名分
Czech mean rank score
2.2 ± 0.02（95% CI） 排名分
Danish mean rank score
2.47 ± 0.02（95% CI） 排名分
Dutch mean rank score
2.25 ± 0.17（95% CI） 排名分
English mean rank score
1.83 ± 0.02（95% CI） 排名分
Estonian mean rank score
2.62 ± 0.03（95% CI） 排名分
Faroese mean rank score
3.54 ± 0.04（95% CI） 排名分
Finnish mean rank score
2.52 ± 0.02（95% CI） 排名分
French mean rank score
2.19 ± 0.18（95% CI） 排名分
German mean rank score
2.46 ± 0.17（95% CI） 排名分
Greek mean rank score
2.62 ± 0.02（95% CI） 排名分
Hungarian mean rank score
2.3 ± 0.02（95% CI） 排名分
Icelandic mean rank score
2.93 ± 0.04（95% CI） 排名分
Italian mean rank score
2.44 ± 0.21（95% CI） 排名分
Latvian mean rank score
2.15 ± 0.03（95% CI） 排名分
Lithuanian mean rank score
2.3 ± 0.03（95% CI） 排名分
Luxembourgish mean rank score
2.37 ± 0.15（95% CI） 排名分
Norwegian mean rank score
2.24 ± 0.08（95% CI） 排名分
Polish mean rank score
2.56 ± 0.02（95% CI） 排名分
Portuguese mean rank score
2.28 ± 0.06（95% CI） 排名分
Romanian mean rank score
2.19 ± 0.02（95% CI） 排名分
Serbian mean rank score
2.2 ± 0.02（95% CI） 排名分
Slovak mean rank score
2.5 ± 0.02（95% CI） 排名分
Slovene mean rank score
2.62 ± 0.03（95% CI） 排名分
Spanish mean rank score
2.44 ± 0.16（95% CI） 排名分
Swedish mean rank score
2.35 ± 0.16（95% CI） 排名分
Ukrainian mean rank score
2.17 ± 0.02（95% CI） 排名分

LumiOpen/Llama-Poro-2-70B-Instruct

Model reported by the benchmark

Test split · few-shot · Instruction-tuned

Mean European-language rank score
Not provided
Faroese mean rank score
2.83 ± 0.07（95% CI） 排名分
More metrics
Albanian mean rank score
Not provided
Belarusian mean rank score
Not provided
Bosnian mean rank score
Not provided
Bulgarian mean rank score
Not provided
Catalan mean rank score
Not provided
Croatian mean rank score
Not provided
Czech mean rank score
Not provided
Danish mean rank score
Not provided
Dutch mean rank score
Not provided
English mean rank score
Not provided
Estonian mean rank score
Not provided
Finnish mean rank score
Not provided
French mean rank score
Not provided
German mean rank score
Not provided
Greek mean rank score
Not provided
Hungarian mean rank score
Not provided
Icelandic mean rank score
Not provided
Italian mean rank score
Not provided
Latvian mean rank score
Not provided
Lithuanian mean rank score
Not provided
Luxembourgish mean rank score
Not provided
Norwegian mean rank score
Not provided
Polish mean rank score
Not provided
Portuguese mean rank score
Not provided
Romanian mean rank score
Not provided
Serbian mean rank score
Not provided
Slovak mean rank score
Not provided
Slovene mean rank score
Not provided
Spanish mean rank score
Not provided
Swedish mean rank score
Not provided
Ukrainian mean rank score
Not provided