OpenAI, proprietary

# GPT-5

> GPT-5 by OpenAI, released August 2025. Ranked #45 of 354 with a Noometry Index of 50.9. API: $1.25 in / $10 out per M tokens. 400K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-5
- Last updated: 2026-10-10
- Title: GPT-5 Benchmarks, Price & Rank (October 2026) | Noometry

GPT-5 by OpenAI ranks 45th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.9. Its strongest category is long context, where it ranks 2nd. API pricing starts at $1.25 per million input tokens and $10 per million output tokens, with a 400K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #45 of 354
- **Index score:** 50.9
- **Evidence:** Confirmed 69 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** August 7, 2025
- **Weights:** Proprietary
- **Reasoning:** Yes
- **Context window:** 400K
- **Max output:** 128K
- **Input price:** $1.25 / M
- **Output price:** $10 / M
- **Blended price:** $3.44 / M
- **Output speed:** 2 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #164 of 219
- **Knowledge cutoff:** September 2024
- **Input:** text, image

## Category scores

Each category score combines every public result we have in that category.

GPT-5 category scores

1.  Coding 50.3
2.  Agentic & Tool Use 33.1
3.  Reasoning 38.3
4.  Math 55.0
5.  Knowledge 56.6
6.  Multimodal 46.8
7.  Multilingual 51.4
8.  Instruction Following 73.8
9.  Long Context 69.5
10.  Writing & Preference 63.4
11.  020406080

GPT-5 category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 50.3 | #47 | 8 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 33.1 | #56 | 5 |
| [Reasoning](https://noometry.com/best/reasoning) | 38.3 | #64 | 12 |
| [Math](https://noometry.com/best/math) | 55.0 | #44 | 7 |
| [Knowledge](https://noometry.com/best/knowledge) | 56.6 | #43 | 8 |
| [Multimodal](https://noometry.com/best/multimodal) | 46.8 | #13 | 3 |
| [Multilingual](https://noometry.com/best/multilingual) | 51.4 | #110 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 73.8 | #113 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 69.5 | #2 | 2 |
| [Writing & Preference](https://noometry.com/best/writing) | 63.4 | #65 | 6 |

## Strengths and weaknesses

Categories where GPT-5 places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GPT-5: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Long Context](https://noometry.com/best/long-context) | 69.5 | +28.6 | #2 of 296, top 1% |
| [Multimodal](https://noometry.com/best/multimodal) | 46.8 | +8.3 | #13 of 128, top 11% |
| [Math](https://noometry.com/best/math) | 55.0 | +18.4 | #44 of 327, top 14% |

### Weakest categories

GPT-5: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Instruction Following](https://noometry.com/best/instruction-following) | 73.8 | +2.6 | #113 of 305, top 38% |
| [Multilingual](https://noometry.com/best/multilingual) | 51.4 | +3.9 | #110 of 297, top 38% |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 33.1 | +2.7 | #56 of 154, top 37% |

## Closest competitors

The models ranked just above and below GPT-5. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GPT-5
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GLM-5.3-Flash](https://noometry.com/models/glm-5-3-flash) | #41 | 51.8 | $0.24 | — | [Compare](https://noometry.com/compare/glm-5-3-flash-vs-gpt-5) |
| [Qwen3.7 Max](https://noometry.com/models/qwen3-7-max) | #42 | 51.5 | $3.75 | — | [Compare](https://noometry.com/compare/gpt-5-vs-qwen3-7-max) |
| [Qwen3.6 Max Preview](https://noometry.com/models/qwen3-6-max-preview) | #43 | 51.5 | $2.92 | — | [Compare](https://noometry.com/compare/gpt-5-vs-qwen3-6-max-preview) |
| [GLM-5.2](https://noometry.com/models/glm-5-2) | #44 | 51.1 | $2.15 | 23 | [Compare](https://noometry.com/compare/glm-5-2-vs-gpt-5) |
| [Muse Spark](https://noometry.com/models/muse-spark) | #46 | 50.6 | — | — | [Compare](https://noometry.com/compare/gpt-5-vs-muse-spark) |
| [Claude Opus 4.5](https://noometry.com/models/claude-opus-4-5) | #47 | 50.5 | $10 | 13 | [Compare](https://noometry.com/compare/claude-opus-4-5-vs-gpt-5) |
| [Muse Spark 1.2](https://noometry.com/models/muse-spark-1-2) | #48 | 50.3 | $2 | — | [Compare](https://noometry.com/compare/gpt-5-vs-muse-spark-1-2) |
| [MiMo-V2.6-Pro](https://noometry.com/models/mimo-v2-6-pro) | #49 | 50.3 | $0.54 | — | [Compare](https://noometry.com/compare/gpt-5-vs-mimo-v2-6-pro) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

GPT-5 Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) | 73.6% | #19 of 32, top 60% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-02-06 |
| [SWE-bench Verified](https://noometry.com/benchmarks/swe-bench-verified) | 71.5% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-02-05 |
| [SWE-bench Verified (bash only)](https://noometry.com/benchmarks/swe-bench-bash-only) | 65% | #16 of 39, top 42% | medium | [SWE-bench](https://www.swebench.com/) | 2025-08-07 |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 88% | Best of 44 | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 81.3% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Aider Polyglot](https://noometry.com/benchmarks/aider-polyglot) | 86.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1418 | #65 of 113, top 58% | medium | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SciCode](https://noometry.com/benchmarks/scicode) | 42.9% | #67 of 121, top 56% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GSO](https://noometry.com/benchmarks/gso-bench) | 6.9% | #20 of 31, top 65% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 39.8% |  |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 60.7% | #30 of 119, top 26% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1398 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1436 | #102 of 294, top 35% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,162 | #34 of 105, top 33% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 807.65 |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [AlgoTune](https://noometry.com/benchmarks/algotune) | 1.67 | #8 of 18, top 45% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

GPT-5 Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 49.6% | #17 of 41, top 42% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Terminal-Bench](https://noometry.com/benchmarks/terminal-bench) | 49.6% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GDPval](https://noometry.com/benchmarks/gdpval) | 34.8% | #6 of 11, top 55% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Remote Labor Index](https://noometry.com/benchmarks/remote-labor-index) | 1.7% | #12 of 14, top 86% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench) | 48.1% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench) | 49.6% | #8 of 24, top 34% | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench) | 48.6% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepResearch Bench](https://noometry.com/benchmarks/deepresearch-bench) | 48.9% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BALROG](https://noometry.com/benchmarks/balrog) | 32.8% | #14 of 35, top 40% | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Search](https://noometry.com/benchmarks/arena-search) | 1133 | #29 of 32, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/search) | 2026-08-24 |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 69.4% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [METR Time Horizons](https://noometry.com/benchmarks/metr-time-horizons) | 69.6% | #10 of 32, top 32% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-5 Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 9.9% | #49 of 83, top 60% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 1.9% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 7.5% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 0% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 56.7% | #31 of 77, top 41% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 72.7% | #19 of 99, top 20% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 65.7% | #45 of 83, top 55% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 44% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 56.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 6% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 12.6% | #42 of 134, top 32% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 37% | #27 of 129, top 21% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-12-08 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 24% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-15 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 29% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-15 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 16% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-15 |
| [EnigmaEval](https://noometry.com/benchmarks/enigmaeval) | 10.5% | #13 of 38, top 35% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EBR-Bench](https://noometry.com/benchmarks/ebr-bench) | 12.7% | #18 of 24, top 75% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-29 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1405 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1416 | #110 of 297, top 38% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 23% | #35 of 74, top 48% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-05 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 16% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 15% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 14% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 90.7% | #35 of 151, top 24% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 40% | #45 of 125, top 36% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 150 | #53 of 213, top 25% |  | [Epoch AI](https://epoch.ai/eci) | 2025-08-07 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 61.4 | #10 of 72, top 14% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

GPT-5 Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 55.4% | #43 of 81, top 54% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-10 |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 37.2% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 18.2% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [FrontierMath Tier 4](https://noometry.com/benchmarks/frontiermath-tier-4) | 22% | #42 of 63, top 67% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-06-11 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 91.4% | #48 of 173, top 28% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-29 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 87.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-08-07 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 46.7% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-20 |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 18% | #51 of 77, top 67% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 64.7% | #7 of 57, top 13% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1407 | #116 of 285, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1399 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 98.1% | Best of 79 | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-29 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 97.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-08-20 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 32.4% | #16 of 68, top 24% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-11-13 |
| [FrontierMath (Feb 2025 set)](https://noometry.com/benchmarks/frontiermath-2025-02) | 27.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-11-13 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 12.5% | #18 of 55, top 33% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-30 |
| [FrontierMath Tier 4 (v1)](https://noometry.com/benchmarks/frontiermath-tier-4-v1) | 6.3% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-08-07 |

### Knowledge

GPT-5 Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 86.2% | #59 of 186, top 32% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2025-10-29 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 85.4% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2025-08-07 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 71.7% |  | minimal | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-20 |
| [Humanity's Last Exam](https://noometry.com/benchmarks/hle) | 25.3% | #13 of 41, top 32% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Humanity's Last Exam](https://noometry.com/benchmarks/hle) | 25.3% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 50.1% | #25 of 77, top 33% | high | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 86.3% | #5 of 58, top 9% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [Confabulations](https://noometry.com/benchmarks/confabulations) (lower is better) | 10.3% | Best of 51 | medium reasoning | [Lech Mazur benchmarks](https://github.com/lechmazur/confabulations) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 15.1% |  |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [Vectara Hallucination Rate](https://noometry.com/benchmarks/vectara-hallucination) (lower is better) | 14.7% | #86 of 96, top 90% |  | [Vectara Hallucination Leaderboard](https://github.com/vectara/hallucination-leaderboard) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 79.2% | #2 of 57, top 4% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1404 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1419 | #108 of 273, top 40% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

GPT-5 Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1232 | #66 of 122, top 55% |  | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1208 |  | high | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [GeoBench](https://noometry.com/benchmarks/geobench) | 81% | #4 of 25, top 16% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [VPCT](https://noometry.com/benchmarks/vpct) | 66% | #4 of 24, top 17% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [VPCT](https://noometry.com/benchmarks/vpct) | 63.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

GPT-5 Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1394 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1397 | #110 of 297, top 38% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1422 | #125 of 285, top 44% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1422 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1410 | #112 of 223, top 51% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1408 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1404 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1416 | #82 of 231, top 36% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1409 | #51 of 211, top 25% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1402 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1360 | #96 of 213, top 46% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1358 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1406 | #99 of 283, top 35% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1402 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1399 | #112 of 226, top 50% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1388 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-5 Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 87.5% | #15 of 57, top 27% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1381 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1388 | #114 of 298, top 39% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-5 Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Fiction.LiveBench](https://noometry.com/benchmarks/fiction-livebench) | 97.2% | Best of 47 | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1399 | #118 of 291, top 41% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1387 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-5 Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1403 |  |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1406 | #114 of 297, top 39% | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1365 | #115 of 295, top 39% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1364 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Short-Story Creative Writing](https://noometry.com/benchmarks/lech-mazur-writing) | 86% | Best of 39 | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1627 | #39 of 115, top 34% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 85.7% | #6 of 57, top 11% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1426 | #89 of 295, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1399 |  | high | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

GPT-5 API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $1.25 | $10 | $0.13 | 2026-10-10 |
| [openai](https://platform.openai.com/docs/models) | $1.25 | $10 | $0.13 | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-5) | $1.25 | $10 | $0.13 | 2026-10-10 |

[All OpenAI API prices →](https://noometry.com/llm-pricing/openai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare GPT-5

-   [GPT-5 vs GPT-4.1](https://noometry.com/compare/gpt-4-1-vs-gpt-5)
-   [GPT-5 vs GLM-5.2](https://noometry.com/compare/glm-5-2-vs-gpt-5)
-   [GPT-5 vs Muse Spark](https://noometry.com/compare/gpt-5-vs-muse-spark)
-   [GPT-5 vs Qwen3.6 Max Preview](https://noometry.com/compare/gpt-5-vs-qwen3-6-max-preview)
-   [GPT-5 vs Claude Opus 4.5](https://noometry.com/compare/claude-opus-4-5-vs-gpt-5)
-   [GPT-5 vs Qwen3.7 Max](https://noometry.com/compare/gpt-5-vs-qwen3-7-max)
-   [GPT-5 vs Muse Spark 1.2](https://noometry.com/compare/gpt-5-vs-muse-spark-1-2)
-   [GPT-5 vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-5)
-   [GPT-5 vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-5)
-   [GPT-5 vs Kimi K3](https://noometry.com/compare/gpt-5-vs-kimi-k3)
-   [GPT-5 vs Grok 4.6](https://noometry.com/compare/gpt-5-vs-grok-4-6)
-   [GPT-5 vs Qwen3.8 Max](https://noometry.com/compare/gpt-5-vs-qwen3-8-max)
-   [GPT-5 vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-5)
-   [GPT-5 vs Muse Spark 1.3](https://noometry.com/compare/gpt-5-vs-muse-spark-1-3)

## Other OpenAI models

-   [GPT-6 Astra](https://noometry.com/models/gpt-6-astra)70.8
-   [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol)65.6
-   [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol)65.0
-   [GPT-5.5 Pro](https://noometry.com/models/gpt-5-5-pro)64.3
-   [GPT-5.5](https://noometry.com/models/gpt-5-5)63.4
-   [GPT-6 Sol](https://noometry.com/models/gpt-6-sol)61.8
-   [GPT-5.4](https://noometry.com/models/gpt-5-4)59.4
-   [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra)59.2

## Frequently asked questions

### How good is GPT-5?

GPT-5 by OpenAI ranks 45th of 354 ranked models on the Noometry Index as of October 2026, with a score of 50.9. Its strongest category is long context, where it ranks 2nd. API pricing starts at $1.25 per million input tokens and $10 per million output tokens, with a 400K-token context window.

### How much does GPT-5 cost?

GPT-5 costs $1.25 per million input tokens and $10 per million output tokens on OpenAI's own API, with cached input at $0.13.

### What is GPT-5's context window?

GPT-5 accepts up to 400K tokens of input and can write up to 128K tokens in one response.

### Is GPT-5 open source?

No. GPT-5 is proprietary and available only through OpenAI's API and partner platforms.

### How fast is GPT-5?

GPT-5 generated about 2 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are GPT-5's strengths and weaknesses?

Relative to other ranked models, GPT-5 places best in long context, multimodal, math and lowest in instruction following, multilingual, agentic & tool use.

### What is GPT-5 best at?

Its best category is long context, where it ranks 2nd on Noometry.

### Cite this page

Noometry. (2026). GPT-5 benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gpt-5

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gpt-5.md).