Noometry

Coding benchmark

FrontierCode leaderboard

As of October 2026, Claude Opus 5.5 has the highest published FrontierCode score on Noometry at 54.6%, out of 37 models with results.

Last verified

About FrontierCode

A description with primary sources is being prepared for this benchmark.

Category
Coding
Introduced
2026
Unit
Percent (random guessing ≈ 0%)
Official site
epoch.ai

Top 15 models

  1. Claude Opus 5.5 54.6%
  2. Claude Fable 5 53.5%
  3. Claude Opus 5 53.4%
  4. GPT-6 Astra 53.3%
  5. Claude Sonnet 5.5 52.1%
  6. Claude Fable 5.1 50.9%
  7. GPT-6.1 Sol 50.2%
  8. GPT-6 Sol 49.3%
  9. Grok 4.6 48%
  10. Grok 4.7 47.6%
  11. GPT-5.6 Sol 47.5%
  12. Claude Opus 4.8 46.5%
  13. Kimi K3 44.2%
  14. Gemini 3.7 Flash 43.6%
  15. GPT-5.5 43%

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

All results

#ModelProviderScoreSettingSourceDate
1Claude Opus 5.5 Anthropic54.6%mediumEpoch AI
2Claude Fable 5 Anthropic53.5%Epoch AI
3Claude Opus 5 Anthropic53.4%maxEpoch AI
4GPT-6 Astra OpenAI53.3%maxEpoch AI
5Claude Sonnet 5.5 Anthropic52.1%xhighEpoch AI
6Claude Fable 5.1 Anthropic50.9%mediumEpoch AI
7GPT-6.1 Sol OpenAI50.2%mediumEpoch AI
8GPT-6 Sol OpenAI49.3%maxEpoch AI
9Grok 4.6 xAI48%Epoch AI
10Grok 4.7 xAI47.6%Epoch AI
11GPT-5.6 Sol OpenAI47.5%Epoch AI
12Claude Opus 4.8 Anthropic46.5%Epoch AI
13Kimi K3 Moonshot AI44.2%Epoch AI
14Gemini 3.7 Flash Google43.6%Epoch AI
15GPT-5.5 OpenAI43%Epoch AI
16Claude Sonnet 5 Anthropic42.7%Epoch AI
17Grok 4.5 xAI42.4%Epoch AI
18GPT-6 Luna OpenAI42.4%maxEpoch AI
19GPT-5.6 Terra OpenAI41.3%Epoch AI
20Gemini 3.8 Flash Google41.2%mediumEpoch AI
21GLM-5.3 Z.ai (Zhipu)40.1%maxEpoch AI
22GPT-5.6 Luna OpenAI39.8%Epoch AI
23Claude Opus 4.7 Anthropic38.5%Epoch AI
24Gemini 3.6 Flash Google34.4%Epoch AI
25GLM-5.3-Flash Z.ai (Zhipu)31.8%maxEpoch AI
26Kimi K2.7 Code Moonshot AI30.1%Epoch AI
27DeepSeek V4 Pro DeepSeek28.6%highEpoch AI
28GPT-5.4 mini OpenAI27%Epoch AI
29Claude Opus 4.6 Anthropic26.6%Epoch AI
30GLM-5.2 Z.ai (Zhipu)24.5%noneEpoch AI
31Claude Sonnet 4.6 Anthropic24.3%Epoch AI
32DeepSeek V4 Flash DeepSeek18.8%Epoch AI
33MiniMax-M3 MiniMax14.7%Epoch AI
34Inkling Thinking Machines Lab14%Epoch AI
35Nemotron 3 Ultra NVIDIA13.6%Epoch AI
36Qwen3.7 Plus Alibaba (Qwen)10.2%Epoch AI
37Mistral Medium Mistral AI8%Epoch AI

Compare the leaders

Other coding benchmarks

Frequently asked questions

Which model has the highest FrontierCode score?

As of October 2026, Claude Opus 5.5 has the highest published FrontierCode score on Noometry at 54.6%, out of 37 models with results.

What is the best open-weight model on FrontierCode?

Kimi K3 has the highest FrontierCode accuracy among open-weight models at 44.2%, ranking 13 of 37 overall.