Project benchmark

CompassBench 2026-07 · Math

OpenCompass · 15 configurations with published scores. Review each metric and its test conditions separately.

Report identity & conditions

Data as of2026-10-19· Report published—. See individual records for run dates and test conditions.

Leaderboard updated

  • This leaderboard uses OpenCompass’s closed benchmark sets. Questions update quarterly, and models may be added between quarters. Quarters and tasks are compared separately.
  • Overall and task scores follow the original leaderboard. We do not recalculate overall weights or interpret scores as question accuracy.
  • The same model configurations appear across five task scopes. Reasoning settings stay in the names; adding row counts does not give a count of unique models.
  • Organizations, parameter counts, release dates and release types follow the report. An open-weight label does not imply an open license; use depends on the model’s terms.
  • Quarterly versions and leaderboard update dates are kept separate. Actual test dates and individual sample counts are not stated.
  • Results: official OpenCompass leaderboard.
  • Quarterly version: 2026-07; leaderboard updated: 2026-08-24.
Read the original report ↗

Compare metrics within the same report. Each chart explains its direction and scope.
See the details for full values and run conditions.

Math score

Original scores from this quarter’s closed benchmark; higher is better. Overall and task values are retained and are not ranked across quarters or tasks.: showing 8 of 15 records with values. See details for configurations and dates.

Chart data · 8 entries
Name points
Claude Opus 5 (high)77.3
Gemini-3.7-Flash76.8
Kimi-K2.6 (high)75.7
Qwen3.8-Max75
Doubao-Seed-2.1-Pro-260628 (high)74.9
Kimi-K3 (high)74.1
Grok-4.6 (high)73
Hy3-preview (high)72.2

Advanced math score

Original scores from this quarter’s closed benchmark; higher is better. Overall and task values are retained and are not ranked across quarters or tasks.: showing 8 of 15 records with values. See details for configurations and dates.

Chart data · 8 entries
Name points
Gemini-3.7-Flash85.6
Grok-4.6 (high)83.8
Kimi-K2.6 (high)82.7
Hy3-preview (high)81
Claude Opus 5 (high)79.9
DeepSeek-V4-Pro79.9
Doubao-Seed-2.1-Pro-260628 (high)79.2
Kimi-K3 (high)79.2

Full results & model versions

15 / 15configurations 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.

Gemini-3.7-Flash

Model reported by the benchmark

As reportedOrganization: Google · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
76.8 分
Advanced math score
85.6 分
Competition math score
67.9 分

GLM-5.3

Model reported by the benchmark

As reportedOrganization: Zhipu AI · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
67.2 分
Advanced math score
77.1 分
Competition math score
57.4 分

Kimi-K3 (high)

Model reported by the benchmark

As reportedOrganization: Moonshot · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 2.8T · Open weights

Math score
74.1 分
Advanced math score
79.2 分
Competition math score
68.9 分

Hy3-preview (high)

Model reported by the benchmark

As reportedOrganization: Tencent · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 295B · Open weights

Math score
72.2 分
Advanced math score
81 分
Competition math score
63.5 分

Doubao-Seed-2.1-Pro-260628 (high)

Model reported by the benchmark

As reportedOrganization: ByteDance · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
74.9 分
Advanced math score
79.2 分
Competition math score
70.5 分

GPT-5.5 (high)

Model reported by the benchmark

As reportedOrganization: OpenAI · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
71.4 分
Advanced math score
73.9 分
Competition math score
68.9 分

GPT-5.6-Sol (high)

Model reported by the benchmark

As reportedOrganization: OpenAI · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
71.4 分
Advanced math score
74.3 分
Competition math score
68.6 分

Kimi-K2.6 (high)

Model reported by the benchmark

As reportedOrganization: Moonshot · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 1T · Open weights

Math score
75.7 分
Advanced math score
82.7 分
Competition math score
68.6 分

Qwen3.8-Max

Model reported by the benchmark

As reportedOrganization: Alibaba · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 2.4T · Open weights

Math score
75 分
Advanced math score
79.2 分
Competition math score
70.8 分

DeepSeek-V4-Pro

Model reported by the benchmark

As reportedOrganization: DeepSeek · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 1.6T · Open weights

Math score
71.2 分
Advanced math score
79.9 分
Competition math score
62.5 分

Grok-4.6 (high)

Model reported by the benchmark

As reportedOrganization: xAI · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
73 分
Advanced math score
83.8 分
Competition math score
62.2 分

DeepSeek-V4-Flash

Model reported by the benchmark

As reportedOrganization: DeepSeek · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 284B · Open weights

Math score
70.4 分
Advanced math score
75 分
Competition math score
65.7 分

Claude Opus 4.8 (high)

Model reported by the benchmark

As reportedOrganization: Anthropic · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
71.5 分
Advanced math score
74.6 分
Competition math score
68.3 分

MiniMax-M3

Model reported by the benchmark

As reportedOrganization: MiniMax · Model details ↗

Chat

Release date reported by the benchmark:

Parameters: 428B · Open weights

Math score
63 分
Advanced math score
74.3 分
Competition math score
51.6 分

Claude Opus 5 (high)

Model reported by the benchmark

As reportedOrganization: Anthropic · Model details ↗

Chat

Release date reported by the benchmark:

API

Math score
77.3 分
Advanced math score
79.9 分
Competition math score
74.7 分