SimpleQA Verified leaderboard
- Gemini 4 Argon leads
- 76.0%
- models measured
- 76
- lead over #2
- +0.4 pts
- median
- 43.0%
Leader on SimpleQA Verified · read October 21
On October 21, 2026, 76 of our catalog's models had a SimpleQA Verified result, and Google Gemini 4 Argon led with 76.0%.
Short factual questions with one checkable answer; it rewards knowing, and not guessing. Share answered correctly.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Gemini 4 ArgonGoogle | 76.0% | 80.5 | $10.00 | |
| 2 | GPT-6 AstraOpenAI | 75.6% | 88.7 | $50.00 | |
| 3 | GPT-6.1 SolOpenAI | 73.9% | 88.7 | $10.00 | |
| 4 | Gemini 3.1 Pro PreviewGoogle | 73.5% | 35.3 | $12.00 | |
| 5 | Claude Opus 5.5Anthropic | 72.2% | 92.2 | $20.00 | |
| 6 | Claude Fable 5.1Anthropic | 70.8% | 89.1 | $50.00 | |
| 7 | Claude Fable 5Anthropic | 70.7% | 82.1 | $50.00 | |
| 8 | Gemini 3.8 FlashGoogle | 69.7% | 70.5 | $4.125 | |
| 9 | GPT-5.6 SolOpenAI | 69.7% | 76.7 | $20.00 | |
| 10 | Gemini 3.7 FlashGoogle | 69.2% | 69.9 | $3.75 | |
| 11 | Gemini 3 Flash PreviewGoogle | 66.8% | 75.8 | $3.00 | |
| 12 | Gemini 3.5 FlashGoogle | 66.2% | 42.8 | $9.00 | |
| 13 | Gemini 3.6 FlashGoogle | 66.2% | 48.3 | $3.75 | |
| 14 | GPT-5.5OpenAI | 63.0% | 67.8 | $30.00 | |
| 15 | GPT-6 SolOpenAI | 60.7% | 82.8 | $10.00 | |
| 16 | Muse Spark 1.2Meta | 60.3% | 65.1 | $4.25 | |
| 17 | Claude Opus 5Anthropic | 59.9% | 81.8 | $25.00 | |
| 18 | Muse Spark 1.1Meta | 57.8% | 48.9 | $4.25 | |
| 19 | Grok 4.7xAI | 56.0% | 75.0 | $6.00 | |
| 20 | Qwen3.7 MaxQwen | 55.8% | 45.1 | $4.425 | |
| 21 | Claude Opus 4.8Anthropic | 53.0% | 66.0 | $25.00 | |
| 22 | DeepSeek V4 Pro 0813DeepSeek | 52.9% | 54.6 | $1.98 | |
| 23 | Claude Opus 4.7Anthropic | 51.7% | 51.1 | $25.00 | |
| 24 | Kimi K3Moonshot AI | 50.6% | 61.8 | $11.936 | |
| 25 | GPT-5OpenAI | 50.1% | 72.2 | $10.00 | |
| 26 | o3OpenAI | 49.4% | 70.7 | $8.00 | |
| 27 | Grok 4.6xAI | 49.3% | 76.4 | $6.00 | |
| 28 | Grok 4.5xAI | 48.3% | 75.5 | $6.00 | |
| 29 | GPT-5.1OpenAI | 48.0% | 53.3 | $10.00 | |
| 30 | Qwen3.8 Max (0902)Qwen | 47.3% | 63.5 | $6.00 | |
| 31 | Claude Opus 4.6Anthropic | 47.0% | 66.9 | $25.00 | |
| 32 | DeepSeek V4 Pro 0423DeepSeek | 47.0% | 35.3 | $1.9105 | |
| 33 | Claude Sonnet 5.5Anthropic | 46.5% | 88.9 | $10.00 | |
| 34 | GPT-5.4 ProOpenAI | 46.3% | Not benchmarked | $180.00 | |
| 35 | Claude Opus 4.5Anthropic | 45.7% | 66.8 | $25.00 | |
| 36 | GPT-5.4OpenAI | 45.1% | 37.7 | $15.00 | |
| 37 | Qwen3.6 PlusQwen | 44.1% | 37.4 | $1.95 | |
| 38 | GPT-5.6 TerraOpenAI | 43.2% | 69.0 | $12.00 | |
| 39 | DeepSeek V4.1 FlashDeepSeek | 42.9% | 77.2 | $0.525 | |
| 40 | GPT-6 LunaOpenAI | 41.4% | 71.4 | $0.50 | |
| 41 | o1OpenAI | 41.1% | 61.7 | $60.00 | |
| 42 | GPT-5.6 LunaOpenAI | 41.0% | 61.5 | $1.20 | |
| 43 | GLM 5.3Z.ai | 41.0% | 73.1 | $1.40 | |
| 44 | Qwen3 235B A22B Thinking 2507Qwen | 40.4% | Not benchmarked | $3.50 | |
| 45 | T InklingThinking Machines | 40.3% | 49.7 | $4.05 | |
| 46 | GPT-5.2OpenAI | 37.1% | 58.9 | $14.00 | |
| 47 | Kimi K2.7 CodeMoonshot AI | 36.5% | 39.1 | $3.35 | |
| 48 | Claude Sonnet 4.6Anthropic | 35.5% | 57.8 | $15.00 | |
| 49 | Kimi K2.6Moonshot AI | 34.9% | 44.2 | $3.41 | |
| 50 | Kimi K2.5Moonshot AI | 34.3% | 58.5 | $2.50 | |
| 51 | GLM 5.2Z.ai | 34.2% | 57.7 | $7.00 | |
| 52 | GLM 5.1Z.ai | 34.0% | 44.0 | $4.40 | |
| 53 | Claude Sonnet 5Anthropic | 33.7% | 63.5 | $10.00 | |
| 54 | DeepSeek V4 Flash 0731DeepSeek | 33.6% | Not benchmarked | $1.32 | |
| 55 | Grok 4.3xAI | 33.2% | 22.5 | $2.50 | |
| 56 | GLM 4.7Z.ai | 32.2% | 33.6 | $1.98 | |
| 57 | GPT-4.1OpenAI | 31.1% | 46.5 | $8.00 | |
| 58 | Claude Sonnet 4.5Anthropic | 30.7% | 59.1 | $15.00 | |
| 59 | GPT-5.4 MiniOpenAI | 29.4% | 28.2 | $4.50 | |
| 60 | GPT-4o (2024-08-06)OpenAI | 26.0% | 23.1 | $10.00 | |
| 61 | Qwen3.5 Plus 2026-04-20Qwen | 25.4% | Not benchmarked | $1.80 | |
| 62 | Claude Haiku 5.5Anthropic | 23.8% | 75.9 | $0.50 | |
| 63 | GPT-5 MiniOpenAI | 21.6% | 59.8 | $2.00 | |
| 64 | Qwen3.5-FlashQwen | 20.3% | 6.2 | $0.26 | |
| 65 | Mistral Large 4Mistral AI | 20.0% | 55.3 | $4.18 | |
| 66 | o4 MiniOpenAI | 19.6% | 68.6 | $4.40 | |
| 67 | T Inkling SmallThinking Machines | 19.1% | 29.9 | $1.20 | |
| 68 | Qwen3.6 FlashQwen | 15.9% | Not benchmarked | $1.125 | |
| 69 | o3 MiniOpenAI | 15.3% | 52.1 | $4.40 | |
| 70 | Claude Haiku 4.5Anthropic | 13.2% | 49.8 | $5.00 | |
| 71 | GPT-4.1 MiniOpenAI | 12.7% | 28.5 | $1.60 | |
| 72 | GPT-5 NanoOpenAI | 11.7% | 34.8 | $0.40 | |
| 73 | GPT-5.4 NanoOpenAI | 11.7% | Not benchmarked | $1.25 | |
| 74 | Gemma 4 31BGoogle | 10.4% | 38.3 | $0.40 | |
| 75 | GPT-4o-mini (2024-07-18)OpenAI | 8.3% | 3.6 | $0.60 | |
| 76 | GPT-4.1 NanoOpenAI | 6.0% | 8.9 | $0.40 |
Only models in our catalog are listed, and each appears once with its best published run. 197 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out.