# GPT-5 Benchmark Scores & Performance

> GPT-5 by OpenAI scores 48.96/100 overall, ranking #109 out of 1033 AI models.

Canonical page: https://benchlm.ai/models/gpt-5

Last updated: November 18, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | OpenAI |
| Source Type | Proprietary |
| Reasoning Type | Reasoning |
| Context Window | 128K |
| Overall Score | 48.96/100 |
| Overall Rank | #109 of 1033 |

## Family & Coverage

- Family: GPT-5
- Variant: reasoning
- Benchmarks covered: 31 of 818
- Sibling models: [GPT-5 mini](/models/gpt-5-mini), [GPT-5 nano](/models/gpt-5-nano)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [τ²-bench results](/benchmarks/tau2-bench) | 84.8% | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 20.9% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [JobBench](/benchmarks/jobbench) | 8.5% | Run by JobBench | [JobBench paper](https://arxiv.org/abs/2605.26329) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1015 | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |

## Coding Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [Vibe Code Bench](/benchmarks/vibecodebench) | 20.09% | Run by Vibe Code Bench | [Vals AI: Vibe Code Bench v1.1](https://www.vals.ai/benchmarks/vibe-code) |
| [AA Coding Index](/benchmarks/aacodingindex) | 37.8% | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA LiveCodeBench](/benchmarks/aalivecodebench) | 84.6% | Carried from an upstream page | [Artificial Analysis: livecodebench leaderboard](https://artificialanalysis.ai/evaluations/livecodebench) |
| [LiveCodeBench (Vals)](/benchmarks/valslivecodebench) | 85.9% | Independent run: Vals AI | [Vals AI: LiveCodeBench leaderboard](https://www.vals.ai/models/openai_gpt-5-2025-08-07) |
| [SWE-bench (Vals)](/benchmarks/valsswebench) | 69.0% | Independent run: Vals AI | [Vals AI: SWE-bench leaderboard](https://www.vals.ai/models/openai_gpt-5-2025-08-07) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AA-MMMU-Pro](/benchmarks/mmmu-pro) | 74.2% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [Design Arena Website](/benchmarks/designarenawebsite) | 1175 | Carried from an upstream page | [OpenRouter model benchmarks](https://openrouter.ai/openai/gpt-5/benchmarks) |

## Reasoning Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AA-LCR](/benchmarks/lcr) | 78.2% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [CritPt](/benchmarks/critpt) | 5.7% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |

## Knowledge Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 23.0% | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 85.4% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA-HLE](/benchmarks/aahle) | 28.5% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -8.7% | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 40.3% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 82.2% | Carried from an upstream page | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |
| [AA MMLU-Pro](/benchmarks/mmlu-pro) | 87.1% | Carried from an upstream page | [Artificial Analysis: mmlu-pro leaderboard](https://artificialanalysis.ai/evaluations/mmlu-pro) |
| [GPQA Diamond (Vals)](/benchmarks/gpqa-diamond) | 85.6% | Independent run: Vals AI | [Vals AI: GPQA Diamond leaderboard](https://www.vals.ai/models/openai_gpt-5-2025-08-07) |
| [MMLU-Pro (Vals)](/benchmarks/mmlu-pro) | 86.5% | Independent run: Vals AI | [Vals AI: MMLU Pro leaderboard](https://www.vals.ai/models/openai_gpt-5-2025-08-07) |

## Instruction Following Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AA-IFBench](/benchmarks/ifbench) | 73.1% | Independent run | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/gpt-5) |

## Multilingual Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AA Global-MMLU-Lite](/benchmarks/global-mmlu-lite) | 90.7% | Carried from an upstream page | [Artificial Analysis: global-mmlu-lite leaderboard](https://artificialanalysis.ai/evaluations/global-mmlu-lite) |

## Mathematics Benchmarks

| Benchmark | Score | Who ran it | Source |
|-----------|-------|------------|--------|
| [AA MATH-500](/benchmarks/math-500) | 99.4% | Carried from an upstream page | [Artificial Analysis: math-500 leaderboard](https://artificialanalysis.ai/evaluations/math-500) |
| [AA AIME 2025](/benchmarks/aaaime2025) | 94.3% | Carried from an upstream page | [Artificial Analysis: aime-2025 leaderboard](https://artificialanalysis.ai/evaluations/aime-2025) |

## Other OpenAI Models

- [GPT-6.2 Astra](/models/gpt-6-2-astra) - Score: 89.35
- [GPT-6.2 Sol](/models/gpt-6-2-sol) - Score: 86.07
- [GPT-6 Astra](/models/gpt-6-astra) - Score: 82.99
- [GPT-6.1 Sol](/models/gpt-6-1-sol) - Score: 81.96
- [GPT-6 Sol](/models/gpt-6-sol) - Score: 75.3
- [GPT-6.1 Terra](/models/gpt-6-1-terra) - Score: 77.08
- [GPT-5.6 Sol](/models/gpt-5-6-sol) - Score: 70.87
- [GPT-5.5 Pro](/models/gpt-5-5-pro) - Score: 70.78
- [GPT-5.6 Terra](/models/gpt-5-6-terra) - Score: 66.32
- [GPT-5.5](/models/gpt-5-5) - Score: 65.85
- [GPT-5.2 Pro](/models/gpt-5-2-pro) - Score: 65.23
- [GPT-5.4 Pro](/models/gpt-5-4-pro) - Score: 66.46
- [GPT-5.4](/models/gpt-5-4) - Score: 64.12
- [GPT-5.3 Codex](/models/gpt-5-3-codex) - Score: 62.16
- [GPT-5.6 Luna](/models/gpt-5-6-luna) - Score: 61.59
- [GPT-6 Luna](/models/gpt-6-luna) - Score: 61.15
- [GPT-5.2](/models/gpt-5-2) - Score: 57.83
- [GPT-5.1](/models/gpt-5-1) - Score: 56.09
- [GPT-5.2-Codex](/models/gpt-5-2-codex) - Score: 54.17
- [GPT-5.4 mini](/models/gpt-5-4-mini) - Score: 52.06
- [GPT-5 mini](/models/gpt-5-mini) - Score: 47.3
- [GPT-5.1-Codex](/models/gpt-5-1-codex) - Score: 48.92
- [o3](/models/o3) - Score: 46.44
- [GPT-5.4 nano](/models/gpt-5-4-nano) - Score: 45.31
- [o3-pro](/models/o3-pro) - Score: 43.87
- [o3-mini](/models/o3-mini) - Score: 38.39
- [GPT-OSS 20B](/models/gpt-oss-20b) - Score: 36.31
- [GPT-5 nano](/models/gpt-5-nano) - Score: 36.21
- [GPT-4.1](/models/gpt-4-1) - Score: 35.63
- [o1](/models/o1) - Score: 35.19
- [o1-preview](/models/o1-preview) - Score: 34.94
- [o1-pro](/models/o1-pro) - Score: 36.29
- [GPT-OSS 120B](/models/gpt-oss-120b) - Score: 31.65
- [GPT-4o](/models/gpt-4o) - Score: 26.03
- [GPT-4.1 mini](/models/gpt-4-1-mini) - Score: 25.6
- [GPT-4o mini](/models/gpt-4o-mini) - Score: 24.58
- [GPT-4 Turbo](/models/gpt-4-turbo) - Score: 20.8
- [GPT-4.1 nano](/models/gpt-4-1-nano) - Score: 20.12
- [GPT-5.1-Codex-Max](/models/gpt-5-1-codex-max) - Score: not computed
- [GPT-4.5](/models/gpt-4-5) - Score: not computed
- [o4-mini](/models/o4-mini) - Score: not computed
- [o1-mini](/models/o1-mini) - Score: not computed
- [GPT-5.2 Instant](/models/gpt-5-2-instant) - Score: not computed
- [GPT-5.3 Instant](/models/gpt-5-3-instant) - Score: not computed
- [GPT-5.3-Codex-Spark](/models/gpt-5-3-codex-spark) - Score: not computed
- [GPT-6 Cyber](/models/gpt-6-cyber) - Score: not computed
- [GPT-5.6 Cyber](/models/gpt-5-6-cyber) - Score: not computed
- [GPT-6 Luna (Decisions)](/models/gpt-6-luna-decisions) - Score: not computed
- [GPT-Live-1](/models/gpt-live-1) - Score: not computed
- [GPT Live Transcribe](/models/gpt-live-transcribe) - Score: not computed
- [GPT Transcribe](/models/gpt-transcribe) - Score: not computed
- [GPT Realtime 2.1](/models/gpt-realtime-2-1) - Score: not computed
- [GPT Realtime 2.1 Mini](/models/gpt-realtime-2-1-mini) - Score: not computed
- [GPT Audio 1.5](/models/gpt-audio-1-5) - Score: not computed
- [GPT Realtime 1.5](/models/gpt-realtime-1-5) - Score: not computed
- [GPT Realtime mini](/models/gpt-realtime-mini) - Score: not computed
- [GPT Realtime](/models/gpt-realtime) - Score: not computed
- [GPT-4o mini TTS](/models/gpt-4o-mini-tts) - Score: not computed
- [GPT-4o mini Audio](/models/gpt-4o-mini-audio) - Score: not computed
- [GPT-4o Audio](/models/gpt-4o-audio) - Score: not computed
- [Whisper large-v3-turbo](/models/whisper-large-v3-turbo) - Score: not computed
- [GPT Realtime 2](/models/gpt-realtime-2) - Score: not computed
