OpenAIo3-pro
o3-pro is an OpenAI proprietary reasoning model, released 10 Jun 2025. Its best configuration (high reasoning effort) ranks #280 of 785 on the BenchLeader Index at 53.7 ±8.0, in the upper half. The ± is the point: 416 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 (66) and lowest in reasoning (39). At $35.00 per million tokens blended it is among the most expensive ranked models. It has been measured at 4 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 7 Oct 2026.
- Blended price
- $35.00/M
- $20.00 in · $80.00 out
- Output speed
- –
- First answer
- –
- Context
- 200k
- Full answer
- –
- Cost per run
- –
- Released
- 10 Jun 2025
- Overall index54
- Reasoning39
- Coding55
- Knowledge62
- Instruction following55
- Multimodal66
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 |
|---|---|---|---|---|---|---|
| low | – | – | – | – | $0.032 | Reasoning 36 |
| medium | – | – | – | – | $0.032 | Long context 72 · Reasoning 38 |
| highbest | 53.7 | #280 | – | – | $0.032 | Coding 55 · Instruction following 55 · Knowledge 62 · Multimodal 66 · Reasoning 39 |
| not stated | 53.4 | #288 | – | – | $0.032 | Agents & tools 17 · Coding 75 · Composite 54 · Instruction following 59 · Knowledge 59 · Reasoning 66 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- high
- not stated
The 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 | low | medium | high | not stated | Source | Trend |
|---|---|---|---|---|---|---|
| GPQA Diamond (AA)not in indexeffort not stated | – | – | – | 84.5%#137 | Artificial Analysis | |
| Kagi LLM Benchmarkeffort not stated | – | – | – | 72.1%#24 | Kagi LLM Benchmark | |
| ARC-AGI-1 | 44.3%#187 | 57.0%#169 | 59.3%#162 | – | ARC Prize | |
| ARC-AGI-2 | 2.1%#201 | 1.9%#205 | 4.9%#177 | – | ARC Prize | |
| LMCAnot in index | – | – | 38.5%#113 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | 86.9%#103 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| WeirdML | 58.2%#52 | – | WeirdML | |
| Aider Polygloteffort not stated | – | 84.9%#2 | Aider polyglot leaderboard |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MCP Atlas | 44.5%#32 | Scale AI SEAL |
Knowledge
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| PRBench Financeeffort not stated | – | 49.1%#13 | Scale AI SEAL | |
| PRBench Legaleffort not stated | – | 49.7%#11 | Scale AI SEAL | |
| MultiNRC | 49.0%#10 | – | Scale AI SEAL |
Instruction following
| Benchmark | high | not stated | Source | Trend |
|---|---|---|---|---|
| MultiChallenge | 62.4%#12 | – | Scale AI SEAL | |
| TutorBencheffort not stated | – | 54.6%#5 | Scale AI SEAL |
Human preference
| Benchmark | medium | Source | Trend |
|---|---|---|---|
| Lech Mazur Creative Writingnot in index | 84.4%#4 | Lech Mazur |
Multimodal
| Benchmark | high | Source | Trend |
|---|---|---|---|
| VISTA | 51.6%#6 | Scale AI SEAL |
Long context
| Benchmark | medium | Source | Trend |
|---|---|---|---|
| Fiction.LiveBench 120k | 88.9%#5 | Fiction.live |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 147.3#67 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 21.9#206 | Artificial Analysis |
Safety & honesty
| Benchmark | high | Source | Trend |
|---|---|---|---|
| MASKnot in indexpossible contamination | 82.5%#22 | Scale AI SEAL |
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 | $0.032 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.288 | – | – |
| Code edit | 6,000 / 1,500 | $0.240 | – | – |
| Agentic coding session | 60,000 / 4,000 | $1.52 | – | – |
| Structured extraction | 2,000 / 200 | $0.056 | – | – |
More from OpenAI
See also
Questions people ask
- What are o3-pro's benchmark scores?
- As of 24 Oct 2026, o3-pro (high effort) scores 53.7 ±8.0 on the BenchLeader Index, strongest in multimodal (66) and weakest in reasoning (39). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
- How does o3-pro rank?
- o3-pro (high effort) is #280 of 785 ranked configurations on 24 Oct 2026. 416 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 o3-pro cost per 1M tokens?
- As of 24 Oct 2026, o3-pro costs $20.00 per 1M input tokens and $80.00 per 1M output tokens, $35.00 blended (three input tokens per output token).
- When was o3-pro released?
- OpenAI released o3-pro on 10 Jun 2025. BenchLeader has results for it at 4 reasoning-effort settings.
Data as of 24 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “o3-pro: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/o3-pro.