Models

Which AI to use

4 team plans · 9 tasks · 40 models · Plan prices read on November 16, 2026 (Microsoft: October 25, 2026) · Scores from November 16, 2026

Every model, one score

40 models

One score for 6 jobs, each counted the same, and each company’s official price for developers. Pick a model to see how its score is made.

Scores from November 16, 2026. Developer prices read on November 16, 2026.

  1. #1Gemini 4 CarbonGoogle · Closed · 12 tests · scored in 3 of 6 jobsSilicon score 92.5Price for developers, per million tokens, input and output: $2 / $10until Nov 30
  2. #2Claude Opus 5.5Anthropic · Closed · 25 tests · scored in 6 of 6 jobsSilicon score 87.3Price for developers, per million tokens, input and output: $4 / $20
  3. #3Claude Fable 5.1Anthropic · Closed · 19 tests · scored in 6 of 6 jobsSilicon score 86.8Price for developers, per million tokens, input and output: $10 / $50
  4. #4Gemini 4 ArgonGoogle · Closed · 13 tests · scored in 4 of 6 jobsSilicon score 85.4Price for developers, per million tokens, input and output: $2 / $10until Nov 30
  5. #5GPT-6.1 SolOpenAI · Closed · 25 tests · scored in 6 of 6 jobsSilicon score 85.3Price for developers, per million tokens, input and output: $2 / $10
  6. #6GPT-6 AstraOpenAI · Closed · 24 tests · scored in 6 of 6 jobsSilicon score 84.9Price for developers, per million tokens, input and output: $10 / $50
  7. #7Claude Opus 5Anthropic · Closed · 21 tests · scored in 6 of 6 jobsSilicon score 82.5Price for developers, per million tokens, input and output: $5 / $25
  8. #8Claude Sonnet 5.5Anthropic · Closed · 17 tests · scored in 4 of 6 jobsSilicon score 82.3Price for developers, per million tokens, input and output: $2 / $10
  9. #9Claude Fable 5Anthropic · Closed · 21 tests · scored in 6 of 6 jobsSilicon score 81.3Price for developers, per million tokens, input and output: $10 / $50
  10. #10GPT-5.6 SolOpenAI · Closed · 23 tests · scored in 6 of 6 jobsSilicon score 80.6Price for developers, per million tokens, input and output: $4 / $20
  11. #11Qwen3.8 MaxAlibaba (Qwen) · Closed · 19 tests · scored in 6 of 6 jobsSilicon score 78.7Price for developers, per million tokens, input and output: No price
  12. #12Muse Spark 1.3Meta · Closed · 15 tests · scored in 3 of 6 jobsSilicon score 78.3Price for developers, per million tokens, input and output: No price
  13. #13GPT-5.5OpenAI · Closed · 23 tests · scored in 6 of 6 jobsSilicon score 77.8Price for developers, per million tokens, input and output: $5 / $30
  14. #14Gemini 3.7 FlashGoogle · Closed · 22 tests · scored in 5 of 6 jobsSilicon score 77.1Price for developers, per million tokens, input and output: No price
  15. #15Gemini 3.8 FlashGoogle · Closed · 22 tests · scored in 5 of 6 jobsSilicon score 76.9Price for developers, per million tokens, input and output: $0.75 / $3.75until Dec 31
  16. #16GPT-6 SolOpenAI · Closed · 23 tests · scored in 6 of 6 jobsSilicon score 75.7Price for developers, per million tokens, input and output: $2 / $10
  17. #17Kimi K3Moonshot AI (Kimi) · Open · 17 tests · scored in 4 of 6 jobsSilicon score 74.8Price for developers, per million tokens, input and output: No price
  18. #18DeepSeek V4.1 FlashDeepSeek · Open · 19 tests · scored in 4 of 6 jobsSilicon score 74.4Price for developers, per million tokens, input and output: $0.30 / $1.20
  19. #19Claude Opus 4.7Anthropic · Closed · 23 tests · scored in 6 of 6 jobsSilicon score 74.2Price for developers, per million tokens, input and output: $5 / $25
  20. #20Claude Opus 4.8Anthropic · Closed · 24 tests · scored in 6 of 6 jobsSilicon score 74.0Price for developers, per million tokens, input and output: $5 / $25
  21. #21Claude Opus 4.6Anthropic · Closed · 23 tests · scored in 6 of 6 jobsSilicon score 72.5Price for developers, per million tokens, input and output: $5 / $25
  22. #22GPT-5.6 TerraOpenAI · Closed · 21 tests · scored in 5 of 6 jobsSilicon score 72.0Price for developers, per million tokens, input and output: $2 / $12
  23. #23Grok 4.6xAI · Closed · 19 tests · scored in 5 of 6 jobsSilicon score 71.8Price for developers, per million tokens, input and output: $2 / $6
  24. #24DeepSeek V4 Pro 0813DeepSeek · Open · 14 tests · scored in 3 of 6 jobsSilicon score 71.8Price for developers, per million tokens, input and output: $1.32 / $3.96
  25. #25GLM-5.3Z.ai (GLM) · Open · 14 tests · scored in 3 of 6 jobsSilicon score 71.8Price for developers, per million tokens, input and output: $1.40 / $4.40
  26. #26Grok 4.5xAI · Closed · 21 tests · scored in 5 of 6 jobsSilicon score 71.3Price for developers, per million tokens, input and output: $2 / $6
  27. #27Grok 4.7xAI · Closed · 17 tests · scored in 4 of 6 jobsSilicon score 70.5Price for developers, per million tokens, input and output: $2 / $6
  28. #28Gemini 3.1 ProGoogle · Closed · 25 tests · scored in 6 of 6 jobsSilicon score 70.1Price for developers, per million tokens, input and output: $2 / $12
  29. #29Claude Sonnet 5Anthropic · Closed · 18 tests · scored in 4 of 6 jobsSilicon score 69.7Price for developers, per million tokens, input and output: $2 / $10
  30. #30Claude Haiku 5.5Anthropic · Closed · 17 tests · scored in 4 of 6 jobsSilicon score 68.8Price for developers, per million tokens, input and output: $0.10 / $0.50
  31. #31GLM-5.2Z.ai (GLM) · Open · 17 tests · scored in 4 of 6 jobsSilicon score 67.5Price for developers, per million tokens, input and output: $1.40 / $4.40
  32. #32GPT-5.6 LunaOpenAI · Closed · 19 tests · scored in 5 of 6 jobsSilicon score 66.7Price for developers, per million tokens, input and output: $0.20 / $1.20
  33. #33GLM-5.3 FlashZ.ai (GLM) · Open · 14 tests · scored in 3 of 6 jobsSilicon score 66.5Price for developers, per million tokens, input and output: $0.15 / $0.50
  34. #34GPT-6 LunaOpenAI · Closed · 22 tests · scored in 5 of 6 jobsSilicon score 64.7Price for developers, per million tokens, input and output: $0.10 / $0.50
  35. #35Kimi K2.6Moonshot AI (Kimi) · Open · 17 tests · scored in 4 of 6 jobsSilicon score 63.8Price for developers, per million tokens, input and output: No price

Few tests yet · no place, the score may still move

  1. No place yetClaude Fable 5.2Anthropic · Closed · 9 tests · scored in 1 of 6 jobs · Few tests yetSilicon score 100.0Price for developers, per million tokens, input and output: $8 / $40
  2. No place yetGPT-6.1 TerraOpenAI · Closed · 9 tests · scored in 2 of 6 jobs · Few tests yetSilicon score 85.1Price for developers, per million tokens, input and output: $1 / $5
  3. No place yetKimi K3.1 ProMoonshot AI (Kimi) · Open · 5 tests · scored in 0 of 6 jobs · Few tests yetSilicon score 78.7Price for developers, per million tokens, input and output: No price
  4. No place yetQwen3.8 Flash NextAlibaba (Qwen) · Open · 8 tests · scored in 1 of 6 jobs · Few tests yetSilicon score 70.2Price for developers, per million tokens, input and output: No price
  5. No place yetInkling 2 SmallThinking Machines Lab · Open · 5 tests · scored in 0 of 6 jobs · Few tests yetSilicon score 69.2Price for developers, per million tokens, input and output: No price

The top score is 100. Scores a few points apart are close, because tests often disagree. A model with few tests yet (scored in fewer than 3 of the 6 jobs, or on too few tests) is listed without a place: its score may still move. Prices are what developers pay: official list prices in US dollars per million tokens, input and output. A team that uses the apps pays per person instead: see Plans and prices.

Back to the models
Moonshot AI (Kimi)Open modelFew tests yet

Kimi K3.1 Pro

Place–None yet: few tests yet

Silicon score78.775.1 to 82.3 with other tests

Price for developersNo token priceno official price per token

Each job on its own · scored in 0 of 6

It does not have enough tests in any single job for a job score of its own yet.

Its tests

Kimi K3.1 Pro took 5 of our tests, from 2 publishers. Its place is among the models we list that took the same test. The share says how much of the score each test decides.

TestResultPlaceShare
Arena AgentArena (LMArena)+3.95 points17 of 3930%
Arena WebDevArena (LMArena)1686 rating12 of 4825%
Arena TextArena (LMArena)1485 rating17 of 4121%
ArXivMathMathArena (ETH Zürich)58.27%5 of 712%
BrokenArXivMathArena (ETH Zürich)61.94%5 of 712%

All its tests are put together in one score, and each of the 6 jobs counts the same, so the total is not a plain average of the job scores. The best model gets 100, and every 10 points less is one typical gap behind it. Few tests yet: it has a job score of its own in only 0 of the 6 jobs, so the score may still move. It is listed, but gets no place.

We count only the page and your answer.Thank you. We counted only this page and your answer.
Next · Model releasesNew models, each with its claim check

Checked plan prices Nov 16, 2026 · scores Nov 16, 2026Corrections