Updated daily at 05:00 UTC
Vision-language
GPT-5.5
- Released
- 23 Apr 2026
- Status
- Legacy
- Context
- 1.1M
- Max output
- 128K
- Input per 1M tokens
- $5.00
- Output per 1M tokens
- $30.00
- Open weights
- No
- License
- proprietary
- Parameters
- —
- Knowledge cutoff
- Dec 2025
- 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 | 45.8 | 26 | 4 of 4 |
| Coding & software engineering | 40.0 | 6 | 4 of 5 |
| Agentic tool use | 54.0 | Not ranked | 1 of 2 |
| Computer & browser use | 13.0 | 5 | 1 of 1 |
| Vision & multimodal understanding | 20.2 | Not ranked | 1 of 3 |
| Factuality & hallucination | 63.0 | 12 | 1 of 1 |
| Human preference | 52.5 | 23 | 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 | 26.0% | Independent | low | 7 Aug 2026 | Epoch AI |
| Chess Puzzles | Puzzles solved | 10.0% | Independent | none | 7 Aug 2026 | Epoch AI |
| DTBench (Decision Theory Benchmark) | Accuracy (capability questions) | 96.0% | Third party | xhigh | — | https://conceptualreasoning.ai/dtbench via Epoch AI |
| Earthborne Rangers (EBR-bench) | Objectives reached | 34.3% | Independent | xhigh | 27 Jul 2026 | Epoch AI |
| LMCA (Language Model Conceptual Argumentation) | Correlation with expert ratings (Pearson r) | 0.5427 | Third party | xhigh | — | https://conceptualreasoning.ai/lmca via Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 56.0% | Independent | xhigh | 24 Jul 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 52.0% | Independent | high | 27 Jul 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 28.0% | Independent | low | 28 Aug 2026 | Epoch AI |
| Mystery Game Puzzles | Puzzles solved | 18.0% | Independent | none | 27 Aug 2026 | Epoch AI |
| SimpleBench | Score (AVG@5) | 69.0% | Third party | unknown | — | https://lmcouncil.ai/benchmarks via Epoch AI |
Scientific reasoning
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| GPQA Diamond | Accuracy | 90.7% | Independent | low | 5 May 2026 | Epoch AI |
| GPQA Diamond | Accuracy | 77.3% | Independent | none | 7 Aug 2026 | Epoch AI |
| Surface Evolver Bench | Mean score (partial credit) | 88.1% | Third party | high | — | https://yhenon.github.io/surface-evolver-llm-eval/ via Epoch AI |
| Surface Evolver Bench | Mean score (partial credit) | 81.3% | 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 | 72.5% | Independent | xhigh | 11 Jun 2026 | Epoch AI |
| FrontierMath Tiers 1-3 | Accuracy | 85.3% | Independent | xhigh | 11 Jun 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 84.4% | Independent | low | 7 Aug 2026 | Epoch AI |
| OTIS Mock AIME 2024-2025 | Accuracy | 57.8% | Independent | none | 7 Aug 2026 | Epoch AI |
Coding & software engineering
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| DeepSWE | Pass@1 | 67.0% | Third party | xhigh | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 64.4% | Third party | high | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 54.0% | Third party | medium | — | https://deepswe.datacurve.ai/ via Epoch AI |
| DeepSWE | Pass@1 | 27.0% | Third party | low | — | https://deepswe.datacurve.ai/ via Epoch AI |
| ExploitBench | Mean capability | 47.4% | Source not stated | unknown | — | Epoch AI via Epoch AI |
| ExploitBench | Mean capability | 41.8% | Source not stated | unknown | — | Epoch AI via Epoch AI |
| ExploitBench | Mean capability | 41.6% | Source not stated | unknown | — | Epoch AI via Epoch AI |
| ExploitBench | Mean capability | 32.6% | Source not stated | unknown | — | Epoch AI via Epoch AI |
| FrontierCode | Main score (Mean@5) | 43.0% | Third party | unknown | — | https://cognition.com/frontiercode via Epoch AI |
| GSO | OPT@1 | 40.2% | Third party | xhigh | — | https://gso-bench.github.io/index.html via Epoch AI |
| MirrorCode | Score | 10.0% | Independent | high | 10 Aug 2026 | Epoch AI |
| PostTrainBench | Average score | 27.2% | Source not stated | xhigh | — | Epoch AI via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 84.7% | Third party | unknown | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 83.1% | Third party | unknown | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 82.2% | Third party | unknown | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 82.0% | Third party | unknown | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| Terminal-Bench 2.0 | Accuracy (mean over trials) | 66.1% | Third party | unknown | — | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI |
| WeirdML (v2) | Average accuracy | 84.9% | Third party | xhigh | — | https://htihle.github.io/weirdml.html via Epoch AI |
| WeirdML (v2) | Average accuracy | 83.9% | Third party | high | — | https://htihle.github.io/weirdml.html via Epoch AI |
| WeirdML (v2) | Average accuracy | 67.2% | Third party | none | — | https://htihle.github.io/weirdml.html via Epoch AI |
Agentic tool use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Deep Research Bench (FutureSearch) | Average score | 54.0% | Third party | high | — | https://evals.futuresearch.ai/#drb via Epoch AI |
| Deep Research Bench (FutureSearch) | Average score | 49.6% | Third party | medium | — | https://evals.futuresearch.ai/#drb via Epoch AI |
| Deep Research Bench (FutureSearch) | Average score | 48.7% | Third party | low | — | https://evals.futuresearch.ai/#drb via Epoch AI |
Computer & browser use
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| OSWorld 2.0 | Binary completion (500 steps) | 13.0% | Third party | xhigh | — | https://osworld-v2.xlang.ai/ via Epoch AI |
Professional knowledge work
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| APEX-Agents | Pass@1 (all rubric criteria met) | 55.1% | Source not stated | unknown | — | Epoch AI via Epoch AI |
Long context
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| CL-bench Life | Tasks solved | 22.2% | Source not stated | high | — | Epoch AI via Epoch AI |
Vision & multimodal understanding
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Furniture Assembly | Score | 44.2% | Independent | xhigh | 10 Sep 2026 | Epoch AI |
Factuality & hallucination
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| SimpleQA Verified | Accuracy (% correct) | 63.0% | Independent | xhigh | 27 Aug 2026 | Epoch AI |
Human preference
| Benchmark | Metric | Value | Provenance | Setting | Evaluated | Source |
|---|---|---|---|---|---|---|
| Document Arena (arena.ai) | Arena score (Elo scale) | 1483 | Independent | — | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Arena score (Elo scale) | 1480 | Independent | high | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 21279 | Independent | — | 13 Sep 2026 | Arena |
| Document Arena (arena.ai) | Votes | 20944 | Independent | high | 13 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1481 | Independent | high | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Arena score (Elo scale) | 1477 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 70635 | Independent | — | 25 Sep 2026 | Arena |
| Text Arena (arena.ai) | Votes | 69008 | Independent | high | 25 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1287 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Arena score (Elo scale) | 1281 | Independent | high | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 26870 | Independent | — | 28 Sep 2026 | Arena |
| Vision Arena (arena.ai) | Votes | 25170 | Independent | high | 28 Sep 2026 | Arena |
Other GPT-5 versions
- GPT-5.6 Cyber10 Aug 2026
- GPT-5.6 Luna9 Jul 2026
- GPT-5.6 Sol9 Jul 2026
- GPT-5.6 Terra9 Jul 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—