OpenAIGPT-5 Pro
GPT-5 Pro is an OpenAI proprietary reasoning model, released 7 Aug 2025. Its best configuration ranks #121 of 785 on the BenchLeader Index at 59.8 ±6.2, in the upper half. The ± is the point: 264 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in multimodal (67) and lowest in reasoning (56). At $41.25 per million tokens blended it is among the most expensive ranked models. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 13 Nov 2025.stale: no new result in six months
- Blended price
- $41.25/M
- $15.00 in · $120.00 out
- Output speed
- –
- First answer
- –
- Context
- 400k
- Full answer
- –
- Cost per run
- –
- Released
- 7 Aug 2025
- Overall index60
- Reasoning56
- Knowledge66
- Multimodal67
Versions
OpenAI has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-5.5 Proxhigh | 23 Apr 2026 | 65.3 | #40 |
| GPT-5.4 Pro | 4 Mar 2026 | 63.3 | #68 |
| GPT-5.2 Proxhigh | 11 Dec 2025 | – | – |
| GPT-5 Prothis page | 7 Aug 2025 | 59.8 | #121 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| medium | – | – | – | – | $0.042 | |
| high | – | – | – | – | $0.042 | Coding 57 · Maths 50 · Reasoning 60 |
| not statedbest | 59.8 | #121 | – | – | $0.042 | Knowledge 66 · Multimodal 67 · Reasoning 56 |
How its index has moved
9 Sept 2026 to 21 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| Humanity's Last Exameffort not stated | – | 31.6%#12 | Scale AI / CAIS | |
| SimpleBench | 61.6%#24 | 61.6%#24 | SimpleBench | |
| Kagi LLM Benchmarkeffort not stated | – | 76.8%#11 | Kagi LLM Benchmark | |
| ARC-AGI-1effort not stated | – | 70.2%#143 | ARC Prize | |
| ARC-AGI-2effort not stated | – | 18.3%#146 | ARC Prize | |
| Chess Puzzlesnot in index | 48.0%#19 | – | Epoch AI Benchmarking Hub |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| DeepSearchQAnot in index | 65.2%#2 |
Maths
| Benchmark | high | Source | Trend |
|---|---|---|---|
| FrontierMath Tiers 1–3 | 55.8%#47 | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 19.5%#55 | Epoch AI Benchmarking Hub |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| PRBench Finance | 51.1%#8 | Scale AI SEAL | |
| PRBench Legal | 49.9%#10 | Scale AI SEAL | |
| MultiNRCpossible contamination | 65.2%#2 | Scale AI SEAL |
Multimodal
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| VISTA | 52.4%#3 | Scale AI SEAL |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 150.6#55 | Epoch AI Benchmarking Hub |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 15.2%#53 | Scale AI SEAL | |
| MASKnot in indexpossible contamination | 86.0%#17 | Scale AI SEAL |
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.042 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.252 | – | – |
| Code edit | 6,000 / 1,500 | $0.270 | – | – |
| Agentic coding session | 60,000 / 4,000 | $1.38 | – | – |
| Structured extraction | 2,000 / 200 | $0.054 | – | – |
More from OpenAI
Compare GPT-5 Pro with…
See also
Questions people ask
- What are GPT-5 Pro's benchmark scores?
- As of 24 Oct 2026, GPT-5 Pro scores 59.8 ±6.2 on the BenchLeader Index, strongest in multimodal (67) and weakest in reasoning (56). That rests on 9 independent benchmark results, and every score on this page links to its publisher.
- How does GPT-5 Pro rank?
- GPT-5 Pro is #121 of 785 ranked configurations on 24 Oct 2026. 264 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does GPT-5 Pro cost per 1M tokens?
- As of 24 Oct 2026, GPT-5 Pro costs $15.00 per 1M input tokens and $120.00 per 1M output tokens, $41.25 blended (three input tokens per output token).
- Is GPT-5 Pro better than GPT-5.6 Sol?
- As of 24 Oct 2026, GPT-5.6 Sol (max) is the better pick for most workloads: it leads on quality (68.0 vs 59.8 on the BenchLeader Index) and costs 5.2× less. The head-to-head page has the benchmark-by-benchmark detail.
- When was GPT-5 Pro released?
- OpenAI released GPT-5 Pro on 7 Aug 2025. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-5 Pro: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gpt-5-pro.