Up to four models
Gemma 3 vs Qwen2.5
On the index (GPT-4 = 100), Gemma 3 scores 113 and Qwen2.5 112. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
11397–129
WeightsOpen
ReleasedMar 2025
Price in / out$0.080 / $0.45
Context131K
Core tests taken1 of 9
11296–128
WeightsOpen
ReleasedSep 2024
Price in / out$0.36 / $0.40
Context33K
Core tests taken2 of 9
Gemma 3 and Qwen2.5 are too close to call (1 point apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 2.1× less.
Test by testthird-party results
Every result as a table
| Test | Gemma 3 | Qwen2.5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 47.7% | 49.1% |
| GeoBench | 52.0% | 62.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 22.5% | 8.1% |
| MATH (level 5) | 74.0% | 63.2% |
| Agents | ||
| DTBench | 52.5% | 62.9% |
| LMCA | 12.3% | 13.4% |
Task length · METR
21 sec
Tests at least two of these models have taken. Bold rows are the core tests.