Updated daily at 05:00 UTC
Vision-language
GPT-5.6 Luna
- Released
- 9 Jul 2026
- Status
- Current
- Context
- 1.1M
- Max output
- 128K
- Input per 1M tokens
- $0.20
- Output per 1M tokens
- $1.20
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- 16 Feb 2026
- Reasoning
- Yes
- Modalities
- text, image → text
Category scores
Out of 100, from independent and third-party results only, by method category-2026-09-29.1.
| Category | Score | Rank | Coverage |
|---|---|---|---|
| Knowledge & reasoning | 43.4 | 30 | 3 of 4 |
| Coding & software engineering | 53.5 | Not ranked | 2 of 5 |
| Agentic tool use | 45.6 | Not ranked | 1 of 2 |
| Vision & multimodal understanding | 17.9 | Not ranked | 1 of 3 |
| Factuality & hallucination | 41.0 | 36 | 1 of 1 |
| Human preference | 49.1 | 30 | 3 of 5 |
Benchmark results
Every result we hold for this model, with who ran it and where it was published.
Knowledge & reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Chess Puzzles | Puzzles solved | 40.0% | Independent | max | 9 Jul 2026 | Epoch AI |
| Chess Puzzles | Puzzles solved | 21.0% | Independent | low | 7 Aug 2026 | Epoch AI |
| Chess Puzzles | Puzzles solved | 2.0% | Independent | none | 7 Aug 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 89.1% | Third party | xhigh | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 88.8% | Third party | max | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 86.7% | Third party | high | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 83.2% | Third party | medium | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 80.0% | Third party | low | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 69.3% | Third party | none | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.4854 | Third party | xhigh | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.4854 | Third party | max | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.4738 | Third party | high | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.4425 | Third party | medium | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.4379 | Third party | low | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.414 | Third party | none | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 21.0% | Independent | max | 28 Jul 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 20.0% | Independent | none | 30 Aug 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 17.0% | Independent | low | 27 Aug 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 12.0% | Independent | medium | 27 Aug 2026 | Epoch AI |
| SimpleBench | Score (AVG@5) | 46.8% | Third party | unknown | — | SimpleBench Leaderboard via Epoch AI |
| SimpleBench | Score (AVG@5) | 46.8% | Third party | xhigh | — | https://lmcouncil.ai/benchmarks via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 91.6% | Independent | max | 9 Jul 2026 | Epoch AI |
| GPQA Diamond | Accuracy | 82.3% | Independent | low | 7 Aug 2026 | Epoch AI |
| GPQA Diamond | Accuracy | 63.6% | Independent | none | 7 Aug 2026 | Epoch AI |
| Surface Evolver Bench | Mean score (partial credit) | 61.9% | Third party | medium | — | https://yhenon.github.io/surface-evolver-llm-eval/ via Epoch AI |
Mathematics
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| FrontierMath Tier 4 | Accuracy | 61.0% | Independent | max | 9 Jul 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 82.1% | Independent | max | 9 Jul 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 41.4% | Independent | low | 29 Aug 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 39.6% | Independent | none | 29 Aug 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 98.3% | Independent | max | 9 Jul 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 66.7% | Independent | low | 7 Aug 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 40.0% | Independent | none | 7 Aug 2026 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DeepSWE | Pass@1 | 67.2% | Third party | max | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 56.9% | Third party | xhigh | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 44.2% | Third party | high | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 11.3% | Third party | medium | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 1.5% | Third party | low | — | https://deepswe.datacurve.ai/ via Epoch AI |
| FrontierCode | Main score (Mean@5) | 39.8% | Third party | unknown | — | https://cognition.com/frontiercode via Epoch AI |
| WeirdML (v2) | Average accuracy | 60.9% | Third party | high | — | https://htihle.github.io/weirdml.html via Epoch AI |
Agentic tool use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| BALROG | Average progress | 45.6% | Third party | max | — | https://balrogai.com/ via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Furniture Assembly | Score | 42.5% | Independent | max | 10 Sep 2026 | Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 41.0% | Independent | max | 10 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Document Arena (arena.ai) | Arena score (Elo scale) | 1462 | Independent | xhigh | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 5766 | Independent | xhigh | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1454 | Independent | xhigh | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 35823 | Independent | xhigh | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1259 | Independent | xhigh | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 10099 | Independent | xhigh | 28 Sep 2026 | Arena |
Other GPT-5 versions
- GPT-5.6 Cyber10 Aug 2026
- GPT-5.6 Sol9 Jul 2026
- GPT-5.6 Terra9 Jul 2026
- GPT-5.523 Apr 2026
- GPT-5.5 Pro23 Apr 2026
- GPT-5.4 mini17 Mar 2026
- GPT-5.4 nano17 Mar 2026
- GPT-5.45 Mar 2026
- GPT-5.4 Pro5 Mar 2026
- GPT-5.3 Instant (gpt-5.3-chat-latest)3 Mar 2026
- GPT-5.211 Dec 2025
- GPT-5.2 Instant (gpt-5.2-chat-latest)11 Dec 2025
- GPT-5.2 Pro11 Dec 2025
- GPT-5.112 Nov 2025
- GPT-5.1 Instant (gpt-5.1-chat-latest)12 Nov 2025
- GPT-57 Aug 2025
- GPT-5 Instant (gpt-5-chat-latest)7 Aug 2025
- GPT-5 mini7 Aug 2025
- GPT-5 nano7 Aug 2025
- GPT-5 Pro7 Aug 2025
- GPT-5.4 Cyber—
- GPT-5.5 Cyber—