Up to four models
GPT-4.1 nano vs Llama 3.3 70B
On the index (GPT-4 = 100), GPT-4.1 nano scores 109 and Llama 3.3 70B 108. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-4.1 nano
10993–125
WeightsClosed
ReleasedApr 2025
Price in / out$0.10 / $0.40
Context1.05M
Core tests taken2 of 9
10892–124
WeightsOpen
ReleasedDec 2024
Price in / out$0.71 / $0.71
Context131K
Core tests taken1 of 9
GPT-4.1 nano and Llama 3.3 70B are too close to call (2 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, and costs 4.1× less.
Test by testthird-party results
GPT-4.1 nano
Llama 3.3 70B
Every result as a table
| Test | GPT-4.1 nano | Llama 3.3 70B |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 48.9% | 47.4% |
| Fiction.LiveBench | 25.0% | 33.3% |
| Maths | ||
| AIME-style maths (OTIS mock) | 28.9% | 5.1% |
| MATH (level 5) | 70.0% | 41.6% |
| Coding | ||
| WeirdML | 19.0% | 14.4% |
| Agents | ||
| DTBench | 52.5% | 59.5% |
| LMCA | 5.5% | 17.5% |
Tests at least two of these models have taken. Bold rows are the core tests.