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 | Moonshot | Qwen | OpenAI |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,432 | Not in our dataset | Not in our dataset | 1,441 |
| LiveBench 1.0General reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 72.0% |
| GPQA DiamondScientific knowledge | 83.3% | 84.5% | 81.7% | Not in our dataset |
| HLEAcademic reasoning | 20.3% | Not in our dataset | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | 85.0% | 84.6% | 82.5% | Not in our dataset |
| SimpleBenchCommonsense reasoning | 53.1% | 39.6% | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | 88.9% | 94.5% | Not in our dataset | Not in our dataset |
| GSOGraduate science | 8.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| AiderCode editing | 81.3% | Not in our dataset | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 69.1% | 71.3% | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | 75.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | 73.9% | Not in our dataset | Not in our dataset | Not in our dataset |
| Terminal-BenchAgentic terminal | Not in our dataset | 35.7% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 6.5% | Not in our dataset | Not in our dataset | 41.9% |
Pricing & context Published USD rates per 1M tokens
| Specification | o3 | Kimi K2 Thinking | 3.5 9B Thinking | GPT-6 Luna Thinking |
|---|---|---|---|---|
| Input | $2 | $0.6 | $0.17 | $0.1 |
| Output | $8 | $2.5 | $0.25 | $0.5 |
| Context window | 200K | 262K | 262K | 1.1M |
| 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.