Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
Specification
openai listing
Context
400K
Max output
128K
Released
2025-08-07
Knowledge cutoff
2024-09-30
Retires
2026-12-11
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · openai list price
Input
$1.25
Output
$10.00
Cache read
$0.125
Cache write
$1.25
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | openai | $0.625 |
| Batch output | openai | $5.00 |
| Priority input | openai | $2.50 |
| Priority output | openai | $20.00 |
Batch input is 50% below the interactive input price at the same listing.
Quality
13 benchmarks · 3 sources
Composite
78th
percentile of 334 scored models
Rank
76 / 334
±0.04 sd
Evidence
13 × 3
3 or more benchmarks, from 2 or more sources
Effort range
8.8
points between effort settings
coding94th2/3 bench
reasoning68th4/4 bench
math76th6/7 bench
knowledge72nd1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| medium | 87th | 9 |
| high | 84th | 13 |
| low | 73rd | 4 |
| minimal | 46th | 5 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Aider polyglot | 88.0 | high · aider diff | Aider | 2025-08-23 |
| ↳ | 86.7 | medium · aider diff | Aider | 2025-08-25 |
| ↳ | 81.3 | low · aider diff | Aider | 2025-08-25 |
| Settings differ by 6.7 points on this benchmark. | ||||
| MATH level 5 | 98.1 ±0.3 | high | Epoch AI | 2025-10-29 |
| ↳ | 97.9 ±0.3 | medium | Epoch AI | 2025-08-20 |
| Settings differ by 0.2 points on this benchmark. | ||||
| FrontierMath-v1 | 48.6 ±2.6 | medium · 2 runs | Epoch AI | 2025-11-13 |
| ↳ | 46.2 ±2.8 | high · 2 runs | Epoch AI | 2025-11-13 |
| Settings differ by 2.4 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 91.4 ±3.7 | high | Epoch AI | 2025-10-29 |
| ↳ | 87.2 ±3.9 | medium | Epoch AI | 2025-08-07 |
| ↳ | 46.7 ±7.5 | minimal | Epoch AI | 2026-07-20 |
| Settings differ by 44.7 points on this benchmark. | ||||
| GPQA diamond | 86.2 ±2.1 | high | Epoch AI | 2025-10-29 |
| ↳ | 85.3 ±2.1 | medium | Epoch AI | 2025-08-07 |
| ↳ | 71.7 ±3.2 | minimal | Epoch AI | 2026-07-20 |
| Settings differ by 14.5 points on this benchmark. | ||||
| SWE-Bench verified | 73.5 ±2.0 | high | Epoch AI | 2026-02-06 |
| ↳ | 71.8 | default · OpenHands | SWE-bench | — |
| ↳ | 71.5 ±2.1 | medium | Epoch AI | 2026-02-05 |
| ↳ | 65.0 | medium · mini-SWE-agent | SWE-bench | — |
| Sources and settings disagree by 8.5 points. Both figures stand. | ||||
| Chess Puzzles | 37.0 ±4.9 | high | Epoch AI | 2025-12-08 |
| ↳ | 29.0 ±4.6 | medium | Epoch AI | 2026-07-15 |
| ↳ | 24.0 ±4.3 | low | Epoch AI | 2026-07-15 |
| ↳ | 16.0 ±3.7 | minimal | Epoch AI | 2026-07-15 |
| Settings differ by 21.0 points on this benchmark. | ||||
| SimpleQA Verified | 50.1 ±1.6 | high | Epoch AI | 2026-08-27 |
| FrontierMath-Tiers-1-3-v2 | 55.4 ±2.9 | high | Epoch AI | 2026-06-10 |
| ↳ | 37.2 ±2.9 | low | Epoch AI | 2026-08-27 |
| ↳ | 18.2 ±2.3 | minimal | Epoch AI | 2026-08-27 |
| Settings differ by 37.2 points on this benchmark. | ||||
| FrontierMath-Tier-4-2025-07-01 | 6.2 ±0.0 | high · 2 runs | Epoch AI | 2025-10-30 |
| ↳ | 3.1 ±3.5 | medium · 2 runs | Epoch AI | 2025-08-07 |
| Settings differ by 3.1 points on this benchmark. | ||||
| Mystery Game Puzzles | 23.0 ±4.2 | high | Epoch AI | 2026-08-05 |
| ↳ | 16.0 ±3.7 | low | Epoch AI | 2026-08-27 |
| ↳ | 15.0 ±3.6 | medium | Epoch AI | 2026-08-27 |
| ↳ | 14.0 ±3.5 | minimal | Epoch AI | 2026-08-27 |
| Settings differ by 9.0 points on this benchmark. | ||||
| FrontierMath-Tier-4-v2 | 21.9 ±6.5 | high | Epoch AI | 2026-06-11 |
| EBR-bench | 12.7 | high | Epoch AI | 2026-06-29 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 35 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| openaivendor | $1.25 | $10.00 | $0.125 | — | 400K 272K | 128K | 2026-12-11 |
| opencode | $1.07 | $8.50 | $0.107 | — | 400K | 128K | — |
| poe | $1.10 | $9.00 | $0.11 | — | 400K | 128K | — |
| 302ai | $1.25 | $10.00 | — | — | 400K | 128K | — |
| abacus | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| azure | $1.25 $1.375 | $10.00 $11.00 | $0.13 $0.1375 $0.125 | — | 400K 272K | 128K | 2027-02-09 |
| azure-cognitive-services | $1.25 | $10.00 | $0.13 | — | 400K | 128K | — |
| cloudflare-ai-gateway | $1.25 | $10.00 | $0.125 | — | 128K | 128K | — |
| databricks | $1.25 | $10.00 | $0.125 | $1.25 | 400K 272K | 128K | — |
| edenai | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| fastrouter | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| gmi · gmi | $1.25 | $10.00 | — | — | 410K | 32K | — |
| helicone | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| impossibl | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| kilo | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| llmgateway | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| llmgateway-providers | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| merge-gateway | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| nano-gpt | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| nearai | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| neon | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| oci · oci | $1.25 | $10.00 | — | — | 272K | 128K | — |
| ofox | $1.25 | $10.00 | $0.13 | — | 400K | 128K | — |
| openrouter | $1.25 | $10.00 | $0.125 | — | 400K 272K | 128K | — |
| orcarouter | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| perplexity | $1.25 | $10.00 | $0.125 | — | — | — | — |
| replicate · replicate | $1.25 | $10.00 | — | — | — | — | — |
| sap-ai-core | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| vercel | $1.25 | $10.00 | $0.125 | — | 400K | 128K | — |
| zenmux | $1.25 | $10.00 | $0.12 | — | 400K | 64K | — |
| cortecs | $1.375 | $10.96 | $0.156 | — | 400K | 128K | — |
| anyapi | — | — | — | — | 400K | 128K | — |
| github_copilot · github-copilot | — | — | — | — | 128K | 128K | — |
| model-oracle-ai | — | — | — | — | 400K | 128K | — |
| qiniu-ai | — | — | — | — | 400K | 128K | — |
Other listings of this model
same model, different key
More from OpenAI
most-hosted first