Skip to content

AI model leaderboard

Factual Q&A and graduate-level scientific knowledge, testing knowledge mastery and answer accuracy.

2 evaluations · 1 organisations · updated 11/13 14:05

Knowledgetop 30

Ranked on the evidence several public evaluations share
The top 30 models, sortable by column
Model
01claude-fable-5-2AnthropicReleased 2026-11-09 · Evidence-sensitiveCached input —Input — · Output —98.8
02Gemini 4 CarbongoogleReleased — · Evidence-sensitiveCached input —Input — · Output —98.3
03gemini-4-argonGoogleReleased 2026-09-30 · Evidence-sensitiveCached input —Input — · Output —97.4
04GPT-6 AstraOpenAIReleased 2026-09-03 · Evidence-sensitiveCached input ¥6.67Input ¥66.68 · Output ¥333.4296.9
05gpt-6.1-sol—Released — · Evidence-sensitiveCached input —Input — · Output —95.5
06Gemini 3.1 Pro PreviewGoogleReleased 2026-02-19 · Evidence-sensitiveCached input ¥1.33Input ¥13.34 · Output ¥80.0294.6
07Claude Opus 5.5AnthropicReleased 2026-09-17 · Evidence-sensitiveCached input ¥1.33Input ¥26.67 · Output ¥133.3791.5
08Gemini 3.8 FlashGoogleReleased 2026-09-02 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0190.3
09Gemini 3.7 FlashGoogleReleased 2026-08-13 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0189.0
10GPT-5.6 SolOpenAIReleased 2026-07-09 · Evidence-sensitiveCached input ¥2.67Input ¥26.67 · Output ¥133.3789.0
11Claude Fable 5AnthropicReleased 2026-06-09 · Evidence-sensitiveCached input ¥6.67Input ¥66.68 · Output ¥333.4288.6
12Gemini 3.6 FlashGoogleReleased 2026-07-21 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0186.5
13Gemini 3.5 FlashGoogleReleased 2026-05-19 · Evidence-sensitiveCached input ¥1Input ¥10 · Output ¥60.0185.4
14Gemini 3 Flash PreviewGoogleReleased 2025-12-17 · Evidence-sensitiveCached input ¥0.33Input ¥3.33 · Output ¥2084.6
15kimi-k3.1-pro-togetherMoonshotReleased 2026-10-23 · Evidence-sensitiveCached input —Input — · Output —82.1
16GPT-5.5OpenAIReleased 2026-04-23 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥200.0581.3
17GPT-6 SolOpenAIReleased 2026-09-22 · Evidence-sensitiveCached input ¥1.33Input ¥13.34 · Output ¥66.6880.0
18Claude Opus 5AnthropicReleased 2026-07-24 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7178.1
19gpt-6-1-terraOpenAIReleased 2026-10-26 · Evidence-sensitiveCached input —Input — · Output —74.4
20Grok 4.7xAIReleased 2026-09-21 · Evidence-sensitiveCached input ¥3.33Input ¥13.34 · Output ¥40.0170.3
21Qwen3.7 MaxAlibabaReleased 2026-05-19 · Evidence-sensitiveCached input ¥2.4Input ¥12 · Output ¥3668.2
22Muse-Spark-Open-816B-A42BMeta AIReleased 2026-10-15 · Evidence-sensitiveCached input —Input — · Output —68.1
23DeepSeek V4 Pro 0813DeepSeekReleased 2026-08-13 · Evidence-sensitiveCached input ¥0.3Input ¥9 · Output ¥2764.9
24Claude Opus 4.8AnthropicReleased 2026-05-28 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7164.5
25Kimi K3Moonshot AIReleased 2026-07-16 · Evidence-sensitiveCached input ¥2Input ¥20 · Output ¥10061.8
26Qwen3.6 Max PreviewAlibabaReleased 2026-04-20 · Evidence-sensitiveCached input ¥0.9Input ¥9 · Output ¥5461.7
27Claude Opus 4.7AnthropicReleased 2026-04-16 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7160.2
28Grok 4.6xAIReleased 2026-08-12 · Evidence-sensitiveCached input ¥3.33Input ¥13.34 · Output ¥40.0158.2
29GPT-5 2025-08-07OpenAIReleased 2025-08-07 · Evidence-sensitiveCached input ¥0.83Input ¥8.34 · Output ¥66.6857.6
30Grok 4.5xAIReleased 2026-07-08 · Evidence-sensitiveCached input ¥2Input ¥13.34 · Output ¥40.0157.1

Each board shows at most 30 models

The consensus index is not an accuracy rate; tied scores keep the order the shared evidence decides.

How to read this board

The current knowledge leaderboard uses two Epoch evaluations, both from the same institution. Prices play no part in the ranking, a missing evaluation does not count as zero, and the index is not an accuracy rate.

How it is calculated

About prices

API prices come from the providers' own sites, per million tokens. Dollar prices are converted to CNY at the rate of 2026-11-12. The cached price is the input price on a cache hit; cache writes, storage and subscriptions are extra.