Aider Benchmarks
Compare code-editing runs across model developers, with reasoning settings, tool versions, edit formats and samples recorded.
Tool benchmarks
1listed reports / snapshots
EVALUATION PLATFORMS
Benchmark platforms
Find benchmark organizations, projects and reports covering model capabilities, coding tasks and user preferences.
10 benchmark platforms · Page 1 of 1
ARC Prize
Compare abstract reasoning, interactive learning and run costs, separated by benchmark version and framework.
Independent reasoning benchmarks
8listed reports / snapshots
Arena (formerly LMArena)
Explore model comparisons on the official leaderboards. The former domain redirects to arena.ai; results are specific to each task board.
Preference benchmarks
0listed reports / snapshots
Artificial Analysis
Compare intelligence scores, text token prices and model release dates.
Independent benchmarks
5listed reports / snapshots
BFCL · Berkeley Function Calling
Compare function calling, web search, memory and multi-turn tasks, alongside run costs and latency.
Independent research
1listed reports / snapshots
DeepSeek Research
Explore the original R1 distillation results for math, knowledge and coding. These developer-reported results apply to the stated model versions.
Developer report
1listed reports / snapshots
EuroEval
Compare generative tasks across 32 European languages, with mean rank scores and 95% confidence intervals separated by split and prompting method.
Multilingual benchmarks
8listed reports / snapshots
LiveBench
Explore results and run costs for long tasks, reasoning, coding, browsing, data analysis, research and document design.
General task benchmarks
3listed reports / snapshots
LiveCodeBench
Compare code-generation Pass@1 by problem release date and difficulty, with configurations and evaluation scope retained.
Code generation benchmarks
1listed reports / snapshots
OpenCompass
Compare overall, knowledge, reasoning, math and coding results by quarter and task.
Chinese & English benchmarks
5listed reports / snapshots