GPT-5.1 (2025-11-13)
Version-pinned snapshot of GPT-5.1 from the November 13, 2025 release. Use this when audits or regulated workflows require deterministic behavior.
- Reasoning
- Tool Calling
- Structured Output
Pricing
Auto routing · per 1M tokens- Input
- $1.25
- Output
- $10.00
- Cache read
- $0.125
Specifications
- Context window
- 1M
- Max output
- 32.8K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1455.4
Overall Rank
#72 / 421
Votes
41,389
Confidence Interval
1451.7 - 1459.1
Category Scores
Coding
#95 / 416
8,367 votes
1491.7
Math
#69 / 404
2,543 votes
1458.5
Longer Query
#79 / 399
10,854 votes
1459.8
Creative Writing
#78 / 419
6,196 votes
1427.7
Instruction Following
#69 / 421
11,099 votes
1449.8
Hard Prompts
#74 / 421
22,276 votes
1476.3
Additional Categories22
Japanese
#35 / 288
456 votes
1461.8
Chinese
#64 / 395
3,381 votes
1498.0
Polish
#69 / 243
1,197 votes
1457.5
Industry Legal And Government
#70 / 393
3,051 votes
1464.2
Exclude Ties
#71 / 421
29,799 votes
1459.1
German
#72 / 320
716 votes
1453.9
Non English
#72 / 421
24,799 votes
1443.5
Industry Mathematical
#73 / 402
1,841 votes
1462.5
Russian
#73 / 385
5,192 votes
1452.7
English
#74 / 421
16,589 votes
1464.3
Hard Prompts English
#74 / 419
8,747 votes
1481.7
Industry Writing And Literature And Language
#75 / 420
9,288 votes
1437.4
Multi Turn
#76 / 419
7,213 votes
1464.2
Expert
#79 / 371
2,597 votes
1480.7
Industry Medicine And Healthcare
#79 / 391
2,593 votes
1470.2
French
#82 / 301
940 votes
1468.1
Industry Entertainment And Sports And Media
#82 / 419
7,525 votes
1421.4
Industry Business And Management And Financial Operations
#83 / 414
7,720 votes
1447.9
Industry Life And Physical And Social Science
#83 / 419
6,814 votes
1470.0
Spanish
#84 / 304
1,206 votes
1445.4
Korean
#89 / 289
651 votes
1396.0
Industry Software And It Services
#96 / 421
14,045 votes
1481.2
Published 2026-11-11 · Matched as GPT-5.1 (High) · CC BY 4.0
LMArena DatasetLeaderboard results
| Benchmark | Score | Rank on NanoGPT |
|---|---|---|
Epoch AI Benchmarking Hub Epoch AI data, CC BY 4.0 · Updated Nov 13, 2026 | ||
SWE-bench Verified | 68.0% | #22 of 28 |
GPQA Diamond | 87.6% | #58 of 119 |
SimpleQA Verified | 48.0% | #34 of 82 |
OTIS Mock AIME 2024–2025 | 88.6% | #63 of 121 |
Chess Puzzles | 42.0% | #35 of 82 |
Mystery Game Puzzles | 19.0% | #52 of 77 |
EQ-Bench 3 | 1527 | #16 of 49 |
UGI Leaderboard UGI Leaderboard data, Apache-2.0 · Updated Oct 16, 2026 | ||
UGI Score | 44.3 | #62 of 149 |
UGI Willingness | 2.8 | #85 of 149 |
UGI Writing | 55.8 | #45 of 149 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
 Recommended | $1.25 | $10.00 | $0.125 | N/A | N/A |
