Inference
EN

INCLUDE

  • In index
  • Multilingual
ModelsModels with a result.12
Top resultBest result on this benchmark.89.8%Claude Opus 5
Top-3 spreadPoints from first to third.3.6 pts
YearYear of release.—

Result and price

9 of 12 results

Results

12 results
#ModelResultThe score from the source.
01Claude Opus 589.8%
02Claude Opus 4.887.6%
03Qwen3.7 Max86.2%
03Claude Opus 4.586.2%
05Qwen3.5 397B85.6%
06Kimi K2.583.3%
07Qwen3.7 Plus83.0%
08Qwen3 235B-A22B (Reasoning)78.7%
09Qwen3 235B-A22B75.6%
10Qwen3 32B (Reasoning)73.7%
11Qwen3 32B70.9%
12QwQ-32B69.7%