GPT-4o Jan 2025
GPT-4o.
8
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Jan 2025
GPT-4o
Jan 2025 snapshot Closed weights
No Epoch Capabilities Index score yet
- Misguided Attention 32.1% #33 /45
- BIG-Bench Extra Hard 6.00% #5 /11
- GAIA 20.9% #55 /64
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BBEH micro average | 22.3% | #4 of 11 | Official leaderboard | |
| Fiction.LiveBench | 66.7% | #22 of 57 | Fiction.live leaderboard, via Epoch AI | |
| BIG-Bench Extra Hard | 6.00% | #5 of 11 | Official leaderboard | |
| Creative Writing v3 | 63.0 | #76 of 120 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Misguided Attention | 32.1% | #33 of 45 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Aider Polyglot | 27.1% | #32 of 46 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GAIA | 20.9% | #55 of 64 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GeoBench | 71% | #27 of 48 | Official leaderboard |