Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
0 benchmarks in common.
4 models selected. 0 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | Google | Microsoft | Mistral AI | Google |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | Not in our dataset | 1,414 | 1,354 |
| GPQA DiamondScientific knowledge | 43.4% | 44.5% | Not in our dataset | 51.5% |
| MMLU ProMulti-task understanding | 60.0% | Not in our dataset | Not in our dataset | 71.6% |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 20.4% | Not in our dataset |
| AIME 2025Mathematics | Not in our dataset | 31.8% | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | 44.0% | Not in our dataset | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Gemma 4 E2B IT Thinking | Phi-4 Mini Reasoning | MistralAI Mistral Large 3 | Gemini 2.0 Flash-Lite Non-thinking |
|---|---|---|---|---|
| Input | Not available | $0.08 | $0.5 | $0.075 |
| Output | Not available | $0.35 | $1.5 | $0.3 |
| Context window | Not available | 128K | 262K | 1.0M |
| 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.