Skip to content
Bencher

TestsBenchmarks · Knowledge

SimpleQA Verified

Short factual parametric-knowledge questions.

% solvedHigher is betterCounts toward:Weights: Research & analysis ×0.6The test's websiteOfficial page ↗

The best 15 · 38 models tested

Top 15 · best setting per model · 38 models, 39 results (38 independent)

Measured by independent testersIndependent Reported by the makerVendor-reported
SimpleQA Verified leaderboard
Thinking levelSetting
1GPT-6 AstraOpenAI75.6%Maxgpt-6-astra_maxIndependent testIndependentEpoch AI ↗—30 Aug 2026
2GPT-6.1 SolOpenAI73.9%Maxgpt-6.1-sol_maxIndependent testIndependentEpoch AI ↗—29 Sep 2026
3Gemini 3.1 Pro (Preview)Google (Gemini / DeepMind)73.5%Highgemini-3.1-pro-preview_highIndependent testIndependentEpoch AI ↗—10 Aug 2026
4Claude Opus 5.5Anthropic72.2%Maxclaude-opus-5-5_maxIndependent testIndependentEpoch AI ↗—22 Sep 2026
5Claude Fable 5.1Anthropic70.8%Maxclaude-fable-5-1_maxIndependent testIndependentEpoch AI ↗—1 Sep 2026
6Claude Fable 5Anthropic70.7%Extra highclaude-fable-5_xhighIndependent testIndependentEpoch AI ↗—10 Aug 2026
7Gemini 3.8 FlashGoogle (Gemini / DeepMind)69.7%Highgemini-3.8-flash_highIndependent testIndependentEpoch AI ↗—2 Sep 2026
8GPT-5.6 SolOpenAI69.7%Maxgpt-5.6-sol_maxIndependent testIndependentEpoch AI ↗—10 Aug 2026
9Gemini 3.7 FlashGoogle (Gemini / DeepMind)69.2%Highgemini-3.7-flash_highIndependent testIndependentEpoch AI ↗—27 Aug 2026
10Gemini 3.5 FlashGoogle (Gemini / DeepMind)66.2%Highgemini-3.5-flash_highIndependent testIndependentEpoch AI ↗—27 Aug 2026
11Gemini 3.6 FlashGoogle (Gemini / DeepMind)66.2%Highgemini-3.6-flash_highIndependent testIndependentEpoch AI ↗—27 Aug 2026
12GPT-5.5OpenAI63.0%Extra highgpt-5.5_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
13GPT-6 SolOpenAI60.7%Maxgpt-6-sol_maxIndependent testIndependentEpoch AI ↗—22 Sep 2026
14Muse Spark 1.2Meta (Meta Superintelligence Labs, Muse)60.3%Extra highmuse-spark-1.2_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
15Claude Opus 5Anthropic59.9%Maxclaude-opus-5_maxIndependent testIndependentEpoch AI ↗—10 Aug 2026
16Muse Spark 1.1Meta (Meta Superintelligence Labs, Muse)57.8%Defaultmuse-spark-1.1Independent testIndependentEpoch AI ↗—31 Aug 2026
17Qwen3.7 MaxQwen (Alibaba)55.8%Defaultqwen3.7-maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
18Claude Opus 4.8Anthropic53.0%Maxclaude-opus-4-8_maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
19DeepSeek V4 Pro (0813)DeepSeek52.9%Maxdeepseek-v4-pro-0813_maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
20Qwen3.6 Max PreviewQwen (Alibaba)52.0%Defaultqwen3.6-max-previewIndependent testIndependentEpoch AI ↗—27 Aug 2026
21Claude Opus 4.7Anthropic51.7%Extra highclaude-opus-4-7_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
22Kimi K3Moonshot AI (Kimi)50.6%Maxkimi-k3_maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
23Grok 4.6SpaceXAI (formerly xAI)49.3%Highgrok-4.6_highIndependent testIndependentEpoch AI ↗—27 Aug 2026
24Grok 4.5SpaceXAI (formerly xAI)48.3%Highgrok-4.5_highIndependent testIndependentEpoch AI ↗—27 Aug 2026
25Qwen3.8 Max (0902)Qwen (Alibaba)47.3%Extra highqwen3.8-max-0902_xhighIndependent testIndependentEpoch AI ↗—2 Sep 2026
26Claude Opus 4.6Anthropic47.0%Maxclaude-opus-4-6_maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
27DeepSeek V4 Pro (Preview, 0423)DeepSeek47.0%Maxdeepseek-v4-pro_maxIndependent testIndependentEpoch AI ↗—27 Aug 2026
28Claude Sonnet 5.5Anthropic46.5%Maxclaude-sonnet-5-5_maxIndependent testIndependentEpoch AI ↗—29 Sep 2026
29GPT-5.4 ProOpenAI46.3%Extra highgpt-5.4-pro-2026-03-05_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
30Qwen3.8 Max (0803)Qwen (Alibaba)45.8%Extra highqwen3.8-max_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
31GPT-5.4OpenAI45.1%Extra highgpt-5.4-2026-03-05_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026
32Qwen3.6 PlusQwen (Alibaba)44.1%Defaultqwen3.6-plusIndependent testIndependentEpoch AI ↗—27 Aug 2026
33Gemini 3.1 Flash-LiteGoogle (Gemini / DeepMind)43.3%HighMaker's own figureVendor-reportedGoogle ↗—3 Mar 2026
34GPT-5.6 TerraOpenAI43.2%Maxgpt-5.6-terra_maxIndependent testIndependentEpoch AI ↗—10 Aug 2026
35GPT-6 LunaOpenAI41.4%Maxgpt-6-luna_maxIndependent testIndependentEpoch AI ↗—22 Sep 2026
36GLM-5.3Z.ai (Zhipu)41.0%Maxglm-5.3_maxIndependent testIndependentEpoch AI ↗—28 Aug 2026
37GPT-5.6 LunaOpenAI41.0%Maxgpt-5.6-luna_maxIndependent testIndependentEpoch AI ↗—10 Aug 2026
38InklingThinking Machines Lab40.3%Extra highInkling_xhighIndependent testIndependentEpoch AI ↗—27 Aug 2026