Noometry

Math benchmark

MathArena Final-Answer Competitions leaderboard

As of October 2026, GPT-5.5 has the highest published MathArena Final-Answer Competitions score on Noometry at 94.3%, out of 29 models with results.

Last verified

About MathArena Final-Answer Competitions

Problems from recent math competitions such as AIME and HMMT, run shortly after each contest so the answers are unlikely to be in training data, averaged across competitions.

Category
Math
Introduced
2025
Format
Final answer
Unit
Percent (random guessing ≈ 0%)
Official site
matharena.ai

Top 15 models

  1. GPT-5.5 94.3%
  2. Claude Opus 4.8 91.8%
  3. Kimi K3 87.8%
  4. Gemini 3.1 Pro Preview 86.5%
  5. GPT-5.4 83.1%
  6. Claude Opus 4.6 78.5%
  7. DeepSeek V4 Pro 76.6%
  8. DeepSeek V4 Flash 76.5%
  9. Gemini 3.5 Flash 76.3%
  10. Claude Opus 4.7 73.6%
  11. Kimi K2.6 72.9%
  12. GPT-5.2 72%
  13. Gemini 3.6 Flash 70.8%
  14. Step 3.7 Flash 68.5%
  15. Gemini 3 Flash Preview 67.6%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1GPT-5.5 OpenAI94.3%xhighMathArena
2Claude Opus 4.8 Anthropic91.8%maxMathArena
3Kimi K3 Moonshot AI87.8%thinkMathArena
4Gemini 3.1 Pro Preview Google86.5%MathArena
5GPT-5.4 OpenAI83.1%xhighMathArena
6Claude Opus 4.6 Anthropic78.5%highMathArena
7DeepSeek V4 Pro DeepSeek76.6%maxMathArena
8DeepSeek V4 Flash DeepSeek76.5%maxMathArena
9Gemini 3.5 Flash Google76.3%MathArena
10Claude Opus 4.7 Anthropic73.6%xhighMathArena
11Kimi K2.6 Moonshot AI72.9%thinkMathArena
12GPT-5.2 OpenAI72%highMathArena
13Gemini 3.6 Flash Google70.8%MathArena
14Step 3.7 Flash StepFun68.5%MathArena
15Gemini 3 Flash Preview Google67.6%MathArena
16GLM-5.2 Z.ai (Zhipu)67.6%MathArena
17GLM-5.1 Z.ai (Zhipu)67.1%MathArena
18Gemini 3 Pro Google67%previewMathArena
19Step 3.5 Flash StepFun66.8%MathArena
20GLM-5 Z.ai (Zhipu)65.7%MathArena
21Kimi K2.5 Moonshot AI62.3%thinkMathArena
22Grok 4.1 Fast xAI60.9%reasoningMathArena
23Nemotron 3 Super NVIDIA60.4%MathArena
24DeepSeek-V3.2-Exp DeepSeek57.7%thinkMathArena
25Qwen3.5 27B Alibaba (Qwen)56.7%MathArena
26Qwen3.5 35B-A3B Alibaba (Qwen)56%MathArena
27Qwen3.5-9B Alibaba (Qwen)48.5%MathArena
28Qwen3-30B-A3B Alibaba (Qwen)47.8%MathArena
29Qwen3-4B Alibaba (Qwen)38.5%MathArena

Compare the leaders

Other math benchmarks

Frequently asked questions

What does MathArena Final-Answer Competitions measure?

Problems from recent math competitions such as AIME and HMMT, run shortly after each contest so the answers are unlikely to be in training data, averaged across competitions.

Which model has the highest MathArena Final-Answer Competitions score?

As of October 2026, GPT-5.5 has the highest published MathArena Final-Answer Competitions score on Noometry at 94.3%, out of 29 models with results.

What is the best open-weight model on MathArena Final-Answer Competitions?

Kimi K3 has the highest MathArena Final-Answer Competitions accuracy among open-weight models at 87.8%, ranking 3 of 29 overall.