Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
1 benchmarks in common.
4 models selected. 1 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | Qwen | Qwen | Mistral AI | DeepSeek |
|---|---|---|---|---|
| LiveBench 1.0General reasoning | 48.4% | 53.5% | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | 41.7% | 39.3% | 46.0% | 50.5% |
| MMLU ProMulti-task understanding | 69.6% | Not in our dataset | 66.8% | 60.6% |
| AIME 2025Mathematics | 19.1% | 20.9% | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | 21.3% | 22.8% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Qwen3-4B (Thinking) Non-thinking | 3 8B Non-thinking | MistralAI Small 3 | v3 Base |
|---|---|---|---|---|
| Input | $0 | $0.117 | $0.075 | $0.257 |
| Output | $0 | $0.455 | $0.2 | $1.029 |
| Context window | 41K | 131K | 256K | 164K |
| Pricing details | Explore pricing → | Explore pricing → | Explore pricing → | Explore pricing → |
How to read this comparison
Each column keeps the exact model version you selected. Shared benchmarks are the intersection of their reported results; “all coverage” also shows where evidence is missing. Missing results never count as zero.
These are published benchmark scores, not a controlled head-to-head test. The available evidence does not establish matching evaluation settings, so we show no cross-model winner highlights or deltas. Composite quality scores are omitted because they can summarize different benchmark sets.
Scores and statistics are computed upstream. This page reads a fixed data snapshot; its date describes the snapshot, not the date of every measurement.