GPT-4o (2024-08-06)
OpenAI's precusor to ChatGPT-4o. Great on English text and code, with significant improvements on text in non-English languages.
- Vision
Pricing
Auto routing · per 1M tokens- Input
- $2.50
- Output
- $10.00
- Cache read
- $1.25
Specifications
- Context window
- 128K
- Max output
- 16.4K
Benchmarks
Benchmarks
Sourced from LMArena.
Arena Score
1335.6
Overall Rank
#245 / 421
Votes
45,499
Confidence Interval
1331.4 - 1339.9
Category Scores
Coding
#263 / 416
7,318 votes
1359.6
Math
#245 / 404
6,826 votes
1308.6
Longer Query
#242 / 399
6,160 votes
1339.0
Creative Writing
#211 / 419
6,756 votes
1327.1
Instruction Following
#243 / 421
18,305 votes
1318.6
Hard Prompts
#264 / 421
12,655 votes
1326.9
Additional Categories21
Japanese
#182 / 288
1,104 votes
1292.5
Korean
#193 / 289
712 votes
1288.8
German
#211 / 320
1,202 votes
1313.0
Industry Writing And Literature And Language
#211 / 420
12,147 votes
1341.3
Industry Entertainment And Sports And Media
#213 / 419
7,043 votes
1325.0
Spanish
#220 / 303
546 votes
1327.6
French
#230 / 301
457 votes
1327.3
Industry Legal And Government
#237 / 393
2,674 votes
1347.4
Non English
#240 / 421
20,213 votes
1316.8
Russian
#240 / 385
5,517 votes
1325.0
Multi Turn
#243 / 419
8,201 votes
1326.7
Industry Medicine And Healthcare
#246 / 390
2,174 votes
1342.3
Exclude Ties
#248 / 421
28,538 votes
1286.1
Industry Life And Physical And Social Science
#249 / 419
7,560 votes
1347.9
Industry Mathematical
#252 / 401
5,805 votes
1313.1
Chinese
#253 / 395
3,778 votes
1331.3
English
#253 / 421
25,286 votes
1348.2
Expert
#258 / 371
2,349 votes
1311.5
Hard Prompts English
#265 / 419
8,010 votes
1337.6
Industry Software And It Services
#271 / 421
11,864 votes
1346.4
Industry Business And Management And Financial Operations
#275 / 414
5,095 votes
1301.8
Published 2026-11-09 · Matched as GPT-4o (2024-08-06) · 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 | ||
FrontierMath v2 (Tiers 1–3) | 0.4% | #83 of 83 |
GPQA Diamond | 49.2% | #107 of 119 |
SimpleQA Verified | 26.0% | #68 of 82 |
OTIS Mock AIME 2024–2025 | 6.4% | #117 of 121 |
Chess Puzzles | 9.0% | #77 of 82 |
Filtered and ranked to models on NanoGPT.
Providers
Auto routing is available for this model. Explicit provider selection is not available.
 Recommended | $2.50 | $10.00 | $1.25 | N/A | N/A |
