Skip to main content

AI Rankings

SimpleQA Verified Leaderboard: AI Models Ranked by Score

This page ranks AI models by their SimpleQA Verified score, using Epoch AI's open benchmark data.

Data updated

What SimpleQA Verified measures

Short factual questions that each have one correct answer. It measures how often a model gets facts right.

Scores are percentages and higher is better. Results come from Epoch AI's open benchmark data; we do not run the test ourselves.

Top 20 at a glance

Tap a model to see its full page: scores, price and how it compares.
Top 20 models on SimpleQA Verified scoreRanked list of 20 items. 1. Gemini 4 Argon, 76.0%; 2. GPT-6 Astra, 75.6%; 3. GPT-6.1 Sol, 73.9%.
  1. Gemini 4 Argon76.0%Released 30 Sep 2026
  2. GPT-6 Astra75.6%Released 3 Sep 2026
  3. GPT-6.1 Sol73.9%Released 29 Sep 2026
  4. Gemini 3.1 Pro73.5%Released 19 Feb 2026
  5. Claude Opus 5.572.2%Released 22 Sep 2026
  6. Claude Fable 5.170.8%Released 1 Sep 2026
  7. Claude Fable 570.7%Released 9 Jun 2026
  8. Gemini 3.8 Flash69.7%Released 2 Sep 2026
  9. GPT-5.6 Sol69.7%Released 9 Jul 2026
  10. Gemini 3.7 Flash69.2%Released 13 Aug 2026
  11. Gemini 3 Flash66.8%Released 17 Dec 2025
  12. Gemini 3.5 Flash66.2%Released 19 May 2026
  13. Gemini 3.6 Flash66.2%Released 21 Jul 2026
  14. GPT-5.563.0%Released 23 Apr 2026
  15. GPT-6 Sol60.7%Released 22 Sep 2026
  16. Muse Spark 1.260.3%Released 5 Aug 2026
  17. Claude Opus 559.9%Released 24 Jul 2026
  18. Muse Spark 1.157.8%Released 9 Jul 2026
  19. Muse Spark Open56.6%Open weightsReleased 15 Oct 2026
  20. Grok 4.756.0%Released 21 Sep 2026

Full ranking

All 82 models.Download the full table (CSV)Data credit: Epoch AI, LiteLLM model price list, used under open licences (details at the foot of the page).
SimpleQA Verified Leaderboard: AI Models Ranked by Score: 82 of 82 models
Rank and modelSimpleQA Verified scoreEpoch indexPrice per 1M tokens (in / out)Released
1Gemini 4 ArgonGoogle
76.0%166.4$2.00 / $10.002026-09-30
2GPT-6 AstraOpenAI
75.6%168.8$10.00 / $50.002026-09-03
3GPT-6.1 SolOpenAI
73.9%168.4$2.00 / $10.002026-09-29
4Gemini 3.1 ProGoogle
73.5%155.3$2.00 / $12.002026-02-19
5Claude Opus 5.5Anthropic
72.2%168.8$4.00 / $20.002026-09-22
6Claude Fable 5.1Anthropic
70.8%166.5$10.00 / $50.002026-09-01
7Claude Fable 5Anthropic
70.7%163.4$10.00 / $50.002026-06-09
8Gemini 3.8 FlashGoogle
69.7%157.4$0.75 / $3.752026-09-02
8GPT-5.6 SolOpenAI
69.7%162.8$4.00 / $20.002026-07-09
10Gemini 3.7 FlashGoogle
69.2%158.0$0.75 / $3.752026-08-13
11Gemini 3 FlashGoogle
66.8%151.9$0.50 / $3.002025-12-17
12Gemini 3.5 FlashGoogle
66.2%154.9$1.50 / $9.002026-05-19
12Gemini 3.6 FlashGoogle
66.2%154.5$0.75 / $3.752026-07-21
14GPT-5.5OpenAI
63.0%159.7$5.00 / $30.002026-04-23
15GPT-6 SolOpenAI
60.7%163.7$2.00 / $10.002026-09-22
16Muse Spark 1.2Meta
60.3%155.1$1.25 / $4.252026-08-05
17Claude Opus 5Anthropic
59.9%163.9$5.00 / $25.002026-07-24
18Muse Spark 1.1Meta
57.8%154.1$1.25 / $4.252026-07-09
19Muse Spark OpenMeta · Open weights
56.6%155.1$1.25 / $4.252026-10-15
20Grok 4.7xAI
56.0%154.4$2.00 / $6.002026-09-21
21Qwen3.7-MaxAlibaba
55.8%154.0$2.50 / $7.502026-05-19
22Claude Opus 4.8Anthropic
53.0%159.0$5.00 / $25.002026-05-28
23DeepSeek V4 Pro 0813DeepSeek · Open weights
52.9%155.6$1.32 / $3.962026-08-13
24Qwen 3.6 Max (Preview)Alibaba
52.0%149.4$1.27 / $7.612026-04-20
25Claude Opus 4.7Anthropic
51.7%156.8$5.00 / $25.002026-04-16
26Kimi K3Moonshot AI · Open weights
50.6%157.9$3.00 / $15.002026-07-16
27GPT-5OpenAI
50.1%150.0$1.25 / $10.002025-08-07
28o3OpenAI
49.4%146.7$2.00 / $8.002025-04-16
29Grok 4.6xAI
49.3%156.6$2.00 / $6.002026-08-12
30Qwen3-MaxAlibaba
48.8%142.3$1.66 / $7.222025-09-24
31Grok 4.5xAI
48.3%154.1$2.00 / $6.002026-07-08
32GPT-5.1OpenAI
48.0%149.8$1.25 / $10.002025-11-13
33Qwen3.8 Max (0902)Alibaba
47.3%155.1Not measured2026-09-01
34Claude Opus 4.6Anthropic
47.0%155.7$5.00 / $25.002026-02-05
35DeepSeek-V4-ProDeepSeek · Open weights
47.0%149.1$1.32 / $3.962026-04-24
36Claude Sonnet 5.5Anthropic
46.5%166.2$2.00 / $10.002026-09-28
37GPT-5.4 ProOpenAI
46.3%159.6$30.00 / $1802026-03-05
38Qwen 3.8 MaxAlibaba
45.8%157.4$2.00 / $6.002026-08-02
39Claude Opus 4.5Anthropic
45.7%150.1$5.00 / $25.002025-11-24
40GPT-5.4OpenAI
45.1%157.3$2.50 / $15.002026-03-05
41Qwen 3.6 PlusAlibaba
44.1%147.3$0.50 / $3.002026-03-31
42GPT-5.6 TerraOpenAI
43.2%160.1$2.00 / $12.002026-07-09
43DeepSeek V4.1 FlashDeepSeek · Open weights
42.9%155.9$0.30 / $1.202026-09-09
44GPT-6 LunaOpenAI
41.4%156.8$0.10 / $0.502026-09-22
45o1OpenAI
41.1%141.7$15.00 / $60.002024-12-17
46GLM-5.3Z.ai · Open weights
41.0%156.0$1.40 / $4.402026-08-14
46GPT-5.6 LunaOpenAI
41.0%156.5$0.20 / $1.202026-07-09
48Qwen3-235B-A22B-Thinking (Jul 2025)Alibaba · Open weights
40.4%143.8$0.30 / $2.902025-07-25
49InklingThinking Machines · Open weights
40.3%148.4$1.00 / $4.052026-07-15
50GPT-5.2OpenAI
37.1%153.7$1.75 / $14.002025-12-11
51Kimi K2.7 CodeMoonshot AI · Open weights
36.5%150.1$0.95 / $4.002026-06-12
52Claude Sonnet 4.6Anthropic
35.5%152.8$3.00 / $15.002026-02-17
53Kimi K2.6Moonshot AI · Open weights
34.9%150.9$0.95 / $4.002026-04-20
54Kimi K2.5Moonshot AI · Open weights
34.3%148.1$0.60 / $3.002026-01-27
55GLM-5.2Z.ai · Open weights
34.2%151.9$1.40 / $4.402026-06-16
56GLM-5.1Z.ai · Open weights
34.0%149.8$1.40 / $4.402026-04-07
57Claude Sonnet 5Anthropic
33.7%156.9$2.00 / $10.002026-06-30
58DeepSeek V4 Flash 0731DeepSeek · Open weights
33.6%154.8$0.19 / $0.382026-07-31
59Grok 4.3 BetaxAI
33.2%148.8Not measured2026-04-17
60GLM-4.7Z.ai · Open weights
32.2%143.6$0.60 / $2.202025-12-22
61GPT-4.1OpenAI
31.1%136.7$2.00 / $8.002025-04-14
62Claude Sonnet 4.5Anthropic
30.7%146.7$3.00 / $15.002025-09-29
63Grok 4.20xAI
30.2%152.1$1.25 / $2.502026-02-17
64GPT-5.4 MiniOpenAI
29.4%148.7$0.75 / $4.502026-03-17
65GPT-4o (Aug 2024)OpenAI
26.0%128.8$2.50 / $10.002024-08-06
66Qwen 3.5 Plus (hosted 397B-A17B)Alibaba
25.4%146.2Not measured2026-02-16
67Claude Haiku 5.5Anthropic
23.8%159.3$0.10 / $0.502026-10-07
68GPT-5 miniOpenAI
21.6%145.3$0.25 / $2.002025-08-07
69Qwen 3.5 Flash (hosted 35B-A3B)Alibaba
20.3%143.5Not measured2026-02-25
70Mistral Large 4Mistral AI
20.0%150.0$0.68 / $2.092026-10-06
71o4-miniOpenAI
19.6%145.5$1.10 / $4.402025-04-16
72Inkling-SmallThinking Machines · Open weights
19.1%150.3$0.47 / $1.202026-07-15
73Qwen 3.6 FlashAlibaba
15.9%142.9Not measured2026-04-27
74o3-miniOpenAI
15.3%140.2$1.10 / $4.402025-01-31
75Claude Haiku 4.5Anthropic
13.2%142.2$1.00 / $5.002025-10-15
76GPT-4.1 miniOpenAI
12.7%134.9$0.40 / $1.602025-04-14
77Claude 3 OpusAnthropic
12.6%126.9$15.00 / $75.002024-02-29
78GPT-5 nanoOpenAI
11.7%139.2$0.05 / $0.402025-08-07
78GPT-5.4 NanoOpenAI
11.7%146.0$0.20 / $1.252026-03-17
80Gemma 4 31B ITGoogle · Open weights
10.4%143.0$0.14 / $0.402026-04-02
81GPT-4o miniOpenAI
8.3%126.5$0.15 / $0.602024-07-18
82GPT-4.1 nanoOpenAI
6.0%129.5$0.10 / $0.402025-04-14

How to read this leaderboard

Scores are percentages and higher is better. For each model we show the best result Epoch lists across its effort settings, the same rule for every model. A gap of a point or two is usually within the normal noise of a test, so treat close scores as a tie. Newer models can be missing when nobody has run the test on them yet, so check the release dates. A benchmark measures one kind of skill: use it together with the overall leaderboard rather than on its own.

Questions people ask

What does SimpleQA Verified measure?

Short factual questions that each have one correct answer. It measures how often a model gets facts right.

Who ran these tests?

The results come from Epoch AI's open benchmark data. It combines runs by Epoch with results published by other groups, and Epoch's own pages say which is which. We do not run tests ourselves.

Does a high score mean the model is best for me?

Not by itself. SimpleQA Verified checks one kind of ability. A model can lead here and still be slower, costlier or a poor fit for your work. Compare it on the overall leaderboard and try it on your own tasks.

Why is a model I know missing?

A model appears only when an open source has published results for it. New models can take days or weeks to be measured, and models with no published score are left out rather than guessed.

Where does the data come from?

Scores come from Epoch AI's open benchmark data (licensed CC BY 4.0). We match models across sources, rank them and show them in charts, without changing the scores. Epoch AI does not endorse this site. Prices and context windows come from the open-source LiteLLM price list (MIT licence), which records each model maker's own price page. Prices change often, so confirm on the maker's site before you buy.

How often is this leaderboard updated?

We check our open data sources every day and show the date of the data at the top of the page. A model only moves when its source publishes new results, so a number can stay the same for weeks.

More leaderboards

Different questions need different tests. Pick the one that matches your work.

Where this data comes from

  • Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
  • LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.

Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake

We use optional cookies for analytics and referral tracking. Learn more about our privacy policy