Updated 9 h ago · first seen 11 Sept 2026
bench_01M293SPE8YX533DB8C6AE1Q1S
- Metric
- accuracy · %
- Direction
- Higher is better
- Results
- 614
- Leader
- gpt-6-astra-xhigh 96.26%
Score history · GPT-5-Codex 1 row
Not enough history to chart — a single observation (83.74% on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 83.74%aa_slug=gpt-5-codex · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
Leaderboard 614 current results
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #601Qwen3-0.6BQwen | 23.94% | aa_slug=qwen3-0.6b-instruct-reasoning · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #602gemma-3-1bGoogle | 23.74% | aa_slug=gemma-3-1b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #603qwen3-5-0-8b-non-reasoningAlibaba Group | 23.64% | aa_slug=qwen3-5-0-8b-non-reasoning · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #604qwen3-0.6b-instructAlibaba Group | 23.13% | aa_slug=qwen3-0.6b-instruct · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #605openchat-35OpenChat | 23.03% | aa_slug=openchat-35 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #606gemma-3n-e2bGoogle | 22.93% | aa_slug=gemma-3n-e2b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #607LFM2-1.2BLiquid AI | 22.83% | aa_slug=lfm2-1-2b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #608llama-2-chat-7bMeta AI | 22.73% | aa_slug=llama-2-chat-7b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #609gemma-3-270mGoogle | 22.42% | aa_slug=gemma-3-270m · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #610llama-3-2-instruct-11b-visionMeta AI | 22.12% | aa_slug=llama-3-2-instruct-11b-vision · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #611Llama-3.2-1BMeta AI | 19.6% | aa_slug=llama-3-2-instruct-1b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #612Mistral 7BMistral AI | 17.68% | aa_slug=mistral-7b-instruct · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #613Qwen3.5-0.8BQwen | 11.11% | aa_slug=qwen3-5-0-8b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #614DeepSeek-R1-Distill-Qwen-1.5BDeepSeek | 9.8% | aa_slug=deepseek-r1-distill-qwen-1-5b · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.
Definition
- Category
- reasoning
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Task
- graduate-level science questions
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Metric
- accuracy · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Direction
- Higher is better
- Paper
- https://arxiv.org/abs/2311.12022
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →
- Evaluated models
- llama-2-chat-7b, grok-3-mini-reasoning, claude-opus-5-medium, gemma-4-12B, deepseek-v4-flash, grok-4-3-low, gemini-2.0-flash-exp, GPT-5.1-Codex Mini +606(614 total)
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Categorycategory1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| reasoning | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Metricmetric1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| accuracy | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Paperpaper1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://arxiv.org/abs/2311.12022 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Tasktask1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| graduate-level science questions | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Unitunit1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| % | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://github.com/idavidrein/gpqa | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 8 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.