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 | Google | Google | Anthropic | MiniMax |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,409 | 1,391 | Not in our dataset |
| LiveBench 1.0General reasoning | Not in our dataset | Not in our dataset | 74.8% | Not in our dataset |
| GPQA DiamondScientific knowledge | 64.7% | 82.8% | 70.0% | 70.0% |
| HLEAcademic reasoning | Not in our dataset | 11.0% | 5.5% | 8.4% |
| MMLU ProMulti-task understanding | 79.1% | Not in our dataset | 83.7% | 81.1% |
| SimpleBenchCommonsense reasoning | Not in our dataset | 41.2% | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | Not in our dataset | 72.0% | 33.1% | 76.9% |
| GSOGraduate science | Not in our dataset | Not in our dataset | 4.9% | Not in our dataset |
| AiderCode editing | Not in our dataset | 55.1% | 56.4% | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | 60.4% | 72.7% | 56.0% |
| LiveCodeBenchCompetitive coding | Not in our dataset | 62.6% | 47.1% | Not in our dataset |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | 75.0% | 63.5% |
| Terminal-BenchAgentic terminal | Not in our dataset | 16.9% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | 2.5% | 1.3% | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Gemini 2.0 Pro Non-thinking | Gemini 2.5 Flash Thinking | Claude Sonnet 4 4.0 Non-thinking | M1 Reasoning 80K |
|---|---|---|---|---|
| Input | Not available | $0.3 | $3 | $0.55 |
| Output | Not available | $2.5 | $15 | $2.2 |
| Context window | Not available | 1.0M | 200K | 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.