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 | OpenAI | Qwen | Qwen | Moonshot |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,456 | Not in our dataset | 1,422 | 1,418 |
| LiveBench 1.0General reasoning | Not in our dataset | 63.6% | Not in our dataset | 76.4% |
| GPQA DiamondScientific knowledge | Not in our dataset | 55.9% | Not in our dataset | 75.1% |
| HLEAcademic reasoning | 6.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | Not in our dataset | 74.0% | Not in our dataset | 81.1% |
| SimpleBenchCommonsense reasoning | 53.2% | Not in our dataset | Not in our dataset | 26.3% |
| AIME 2025Mathematics | Not in our dataset | 65.6% | Not in our dataset | 49.5% |
| GSOGraduate science | 13.7% | Not in our dataset | Not in our dataset | 4.9% |
| AiderCode editing | Not in our dataset | Not in our dataset | Not in our dataset | 60.0% |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | Not in our dataset | 65.8% |
| LiveCodeBenchCompetitive coding | Not in our dataset | 54.2% | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 70.6% |
| Terminal-BenchAgentic terminal | 47.6% | Not in our dataset | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 0.4% | Not in our dataset | 1.3% | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-5.1 | Qwen3-4B (Thinking) Thinking | 3 235B A22B non-thinking-2507 | Kimi K2 0711 Preview |
|---|---|---|---|---|
| Input | $1.25 | $0 | $0.14 | $0.57 |
| Output | $10 | $0 | $0.8 | $2.3 |
| Context window | 400K | 41K | 262K | 131K |
| 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.