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 | MiniMax | Anthropic | Moonshot | Qwen |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,391 | 1,418 | 1,422 |
| LiveBench 1.0General reasoning | Not in our dataset | 74.8% | 76.4% | Not in our dataset |
| GPQA DiamondScientific knowledge | 70.0% | 70.0% | 75.1% | Not in our dataset |
| HLEAcademic reasoning | 8.4% | 5.5% | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | 81.1% | 83.7% | 81.1% | Not in our dataset |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 26.3% | Not in our dataset |
| AIME 2025Mathematics | 76.9% | 33.1% | 49.5% | Not in our dataset |
| GSOGraduate science | Not in our dataset | 4.9% | 4.9% | Not in our dataset |
| AiderCode editing | Not in our dataset | 56.4% | 60.0% | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 56.0% | 72.7% | 65.8% | Not in our dataset |
| LiveCodeBenchCompetitive coding | Not in our dataset | 47.1% | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | 63.5% | 75.0% | 70.6% | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | 1.3% | Not in our dataset | 1.3% |
Pricing & context Published USD rates per 1M tokens
| Specification | M1 Reasoning 80K | Claude Sonnet 4 4.0 Non-thinking | Kimi K2 0711 Preview | 3 235B A22B non-thinking-2507 |
|---|---|---|---|---|
| Input | $0.55 | $3 | $0.57 | $0.14 |
| Output | $2.2 | $15 | $2.3 | $0.8 |
| Context window | 1.0M | 200K | 131K | 262K |
| 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.