Skip to content
e/acc model frontier · Consensus rankings from public benchmarks

Where is the frontier now?

Rankings draw on real public benchmarks across capabilities. Consensus indices are not accuracy, missing results are not zero, and prices do not affect ranks.
Time machineAcceleration

Factual questions and graduate-level science test knowledge and answer accuracy.

2 benchmarks·1 organizations·10/17 08:05New

Knowledge boardTOP 30

Ranked by shared evidence across public benchmarks
Sortable top 30 models
Models
01Gemini 4 ArgonGoogleReleased2026-09-30 · Evidence-sensitiveCached input—Input—· Output—97.4
02GPT-6 AstraOpenAIReleased2026-09-03 · Evidence-sensitiveCached input¥6.69Input¥66.86· Output¥334.3197.0
03GPT-6.1 SolOpenAIReleased— · Evidence-sensitiveCached input—Input—· Output—95.6
04Gemini 3.1 Pro PreviewGoogleReleased2026-02-19 · Evidence-sensitiveCached input¥1.34Input¥13.37· Output¥80.2395.0
05Claude Opus 5.5AnthropicReleased2026-09-17 · Evidence-sensitiveCached input¥1.34Input¥26.74· Output¥133.7292.9
06Claude Fable 5AnthropicReleased2026-06-09 · Evidence-sensitiveCached input¥6.69Input¥66.86· Output¥334.3190.2
07Gemini 3.8 FlashGoogleReleased2026-09-02 · Evidence-sensitiveCached input¥0.5Input¥5.01· Output¥25.0789.7
08GPT-5.6 SolOpenAIReleased2026-07-09 · Evidence-sensitiveCached input¥2.67Input¥26.74· Output¥133.7289.0
09Gemini 3.7 FlashGoogleReleased2026-08-13 · Evidence-sensitiveCached input¥0.5Input¥5.01· Output¥25.0788.7
10Gemini 3.6 FlashGoogleReleased2026-07-21 · Evidence-sensitiveCached input¥0.5Input¥5.01· Output¥25.0784.7
11Gemini 3 Flash PreviewGoogleReleased2025-12-17 · Evidence-sensitiveCached input¥0.33Input¥3.34· Output¥20.0684.6
12Gemini 3.5 FlashGoogleReleased2026-05-19 · Evidence-sensitiveCached input¥1Input¥10.03· Output¥60.1884.5
13GPT-5.5OpenAIReleased2026-04-23 · Evidence-sensitiveCached input¥3.34Input¥33.43· Output¥200.5979.7
14GPT-6 SolOpenAIReleased2026-09-22 · Evidence-sensitiveCached input¥1.34Input¥13.37· Output¥66.8677.4
15Claude Opus 5AnthropicReleased2026-07-24 · Evidence-sensitiveCached input¥3.34Input¥33.43· Output¥167.1675.7
16Grok 4.7xAIReleased2026-09-21 · Evidence-sensitiveCached input¥3.34Input¥13.37· Output¥40.1270.1
17Muse-Spark-Open-816B-A42BMeta AIReleased2026-10-15 · Evidence-sensitiveCached input—Input—· Output—70.0
18Qwen3.7 MaxAlibabaReleased2026-05-19 · Evidence-sensitiveCached input¥2.4Input¥12· Output¥3669.2
19DeepSeek V4 Pro 0813DeepSeekReleased2026-08-13 · Evidence-sensitiveCached input¥0.3Input¥9· Output¥2764.6
20Claude Opus 4.8AnthropicReleased2026-05-28 · Evidence-sensitiveCached input¥3.34Input¥33.43· Output¥167.1664.5
21Qwen3.6 Max PreviewAlibabaReleased2026-04-20 · Evidence-sensitiveCached input¥0.9Input¥9· Output¥5460.9
22Claude Opus 4.7AnthropicReleased2026-04-16 · Evidence-sensitiveCached input¥3.34Input¥33.43· Output¥167.1659.7
23Kimi K3Moonshot AIReleased2026-07-16 · Evidence-sensitiveCached input¥2Input¥20· Output¥10058.8
24GPT-5 2025-08-07OpenAIReleased2025-08-07 · Evidence-sensitiveCached input¥0.84Input¥8.36· Output¥66.8655.8
25Grok 4.6xAIReleased2026-08-12 · Evidence-sensitiveCached input¥3.34Input¥13.37· Output¥40.1254.6
26Grok 4.5xAIReleased2026-07-08 · Evidence-sensitiveCached input¥2.01Input¥13.37· Output¥40.1253.3
27Qwen3 Max 2025-09-23AlibabaReleased2025-09-24 · Evidence-sensitiveCached input—Input¥6· Output¥2452.7
28GPT-5.1 2025-11-13OpenAIReleased2025-11-13 · Evidence-sensitiveCached input¥0.84Input¥8.36· Output¥66.8652.6
29Qwen3.8 Max 0902AlibabaReleased2026-09-01 · Evidence-sensitiveCached input—Input¥12· Output¥3652.5
30Claude Sonnet 5.5AnthropicReleased— · Evidence-sensitiveCached input—Input—· Output—52.0

Up to 30 models per board

The consensus index is not accuracy. Tied scores retain ranks determined by the full evidence.

How to read this board

The current knowledge board uses two Epoch benchmarks from the same organization.Prices do not affect rank, missing results are not zero, and the index is not accuracy.

Read the methodology →

About prices

API prices come from vendor websites and are shown per million tokens.USD prices are converted to CNY at 2026-10-16.Cached prices cover cache-hit input. Cache writes, storage and subscriptions are separate.

How fast the same capability gets cheaper: the cost of intelligence →