benchmarks / simpleqa
SimpleQA Verified
accuracy. Status display_only. Contamination risk low. Maintainer Epoch AI. Source.
Display only.This benchmark cannot decide a crown under methodology v1.0.
| Model | Score | Date | Kind |
|---|---|---|---|
| Gemini 4 Argon | 0.76 | 2026-09-30 | observation |
| DeepSeek V4.1 Flash | 0.429 | 2026-09-09 | observation |
| Claude Haiku 5.5 | 0.238 | 2026-10-07 | observation |
| Mistral Large 4.0 | 0.2 | 2026-10-06 | observation |
| GPT-6.1 Sol | 0.739 | 2026-09-29 | observation |
| Claude Sonnet 5.5 | 0.465 | 2026-09-28 | observation |
| GPT-6 Luna | 0.414 | 2026-09-22 | observation |
| Grok 4.7 | 0.56 | 2026-09-21 | observation |
| GPT-6 Sol | 0.607 | 2026-09-22 | observation |
| Claude Opus 5.5 | 0.722 | 2026-09-22 | observation |
| Qwen3 8 Max 0902 | 0.473 | 2026-09-01 | observation |
| Gemini 3.8 Flash | 0.697 | 2026-09-02 | observation |
| Claude Fable 5.1 | 0.708 | 2026-09-01 | observation |
| GPT-4O Mini | 0.083 | 2024-07-18 | observation |
| GPT-4O | 0.26 | 2024-08-06 | observation |
| GPT-4.1 Nano | 0.06 | 2025-04-14 | observation |
| GPT-4.1 Mini | 0.127 | 2025-04-14 | observation |
| GPT-4.1 | 0.311 | 2025-04-14 | observation |
| O3 Mini | 0.153 | 2025-01-31 | observation |
| O1 | 0.411 | 2024-12-17 | observation |
| Muse Spark 1.1 | 0.5778894472361809 | 2026-07-09 | observation |
| Claude 3 Opus | 0.126 | 2024-02-29 | observation |
| GPT-6 Astra | 0.756 | 2026-09-03 | observation |
| GLM 5.3 | 0.41 | 2026-08-14 | observation |
| Qwen3 5 Plus | 0.2535070140280561 | 2026-02-16 | observation |
| Muse Spark 1.2 | 0.6030150753768844 | 2026-08-05 | observation |
| Inkling | 0.403 | 2026-07-15 | observation |
| Qwen3 235B A22b Thinking 2507 | 0.4044044044044044 | 2025-07-25 | observation |
| GLM 5.1 | 0.34 | 2026-04-07 | observation |
| Inkling Small | 0.191 | 2026-07-15 | observation |