GPT 4.1 Mini
Mid-sized GPT 4.1, comparable to GPT4o with a far higher context window, at lower cost and with higher speed.
- Native PDF input
Added Sep 10, 2025
Pricing
Auto routing · per 1M tokens- Input
- $0.40
- Output
- $1.60
- Cache read
- $0.10
Specifications
- Context window
- 1M
- Max output
- 32.8K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1382.9
Overall Rank
#192 / 421
Votes
38,659
Confidence Interval
1378.6 - 1387.3
Category Scores
Coding
#185 / 416
6,817 votes
1433.0
Math
#216 / 404
2,671 votes
1353.0
Longer Query
#187 / 399
7,062 votes
1389.7
Creative Writing
#184 / 419
5,077 votes
1348.8
Instruction Following
#190 / 421
9,992 votes
1373.1
Hard Prompts
#190 / 421
16,057 votes
1402.6
Additional Categories22
German
#139 / 320
1,053 votes
1393.1
Korean
#149 / 289
807 votes
1346.9
Japanese
#156 / 288
1,002 votes
1328.6
Polish
#158 / 243
2,670 votes
1378.9
French
#163 / 301
582 votes
1407.4
Industry Legal And Government
#179 / 393
2,436 votes
1396.6
Multi Turn
#179 / 419
6,996 votes
1393.1
Industry Entertainment And Sports And Media
#187 / 419
6,723 votes
1347.9
Industry Writing And Literature And Language
#189 / 420
8,625 votes
1360.5
English
#190 / 421
18,032 votes
1396.6
Hard Prompts English
#190 / 419
7,664 votes
1413.1
Industry Business And Management And Financial Operations
#190 / 414
6,005 votes
1379.3
Industry Software And It Services
#190 / 421
12,388 votes
1418.2
Exclude Ties
#191 / 421
27,434 votes
1358.9
Non English
#193 / 421
20,621 votes
1361.3
Spanish
#193 / 304
803 votes
1367.8
Russian
#194 / 385
3,081 votes
1367.8
Industry Medicine And Healthcare
#195 / 391
2,304 votes
1395.2
Expert
#203 / 371
2,020 votes
1383.3
Industry Life And Physical And Social Science
#203 / 419
6,484 votes
1384.8
Chinese
#211 / 395
2,544 votes
1383.8
Industry Mathematical
#214 / 402
2,478 votes
1364.1
Published 2026-11-11 · Matched as GPT-4.1 mini (2025-04-14) · 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 17, 2026 | ||
Epoch Capabilities Index | 134.2 | #102 of 115 |
FrontierMath v2 (Tiers 1–3) | 6.7% | #80 of 83 |
GPQA Diamond | 65.8% | #95 of 119 |
SimpleQA Verified | 12.7% | #77 of 82 |
OTIS Mock AIME 2024–2025 | 44.7% | #104 of 121 |
Chess Puzzles | 1.0% | #81 of 82 |
Mystery Game Puzzles | 7.0% | #73 of 77 |
Creative Writing v3 | 1145 | #80 of 96 |
EQ-Bench 3 | 1097 | #35 of 49 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
Recommended | $0.40 | $1.60 | $0.10 | N/A | N/A |