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 | Mistral AI | Zhipu AI | Qwen |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,364 | 1,305 | 1,373 | Not in our dataset |
| LiveBench 1.0General reasoning | 70.0% | Not in our dataset | Not in our dataset | Not in our dataset |
| GPQA DiamondScientific knowledge | 77.0% | 70.8% | Not in our dataset | 73.4% |
| HLEAcademic reasoning | 13.4% | Not in our dataset | 10.6% | 9.8% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | 81.4% | 80.9% |
| SimpleBenchCommonsense reasoning | 22.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | 86.5% | 64.9% | Not in our dataset | 85.0% |
| GSOGraduate science | 1.3% | Not in our dataset | 2.9% | Not in our dataset |
| AiderCode editing | 60.4% | 47.1% | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 49.3% | Not in our dataset | 57.6% | 22.0% |
| LiveCodeBenchCompetitive coding | 67.4% | 59.4% | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | 57.6% | Not in our dataset | 77.9% | Not in our dataset |
| ARC-AGI-2Visual reasoning | 3.0% | 0.0% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | o3 Mini o3-mini | MistralAI Magistral Medium Thinking | GLM-4.5 Air Thinking | 3 30B A3B Thinking (2507) |
|---|---|---|---|---|
| Input | $1.1 | $2 | $0.13 | $0.12 |
| Output | $4.4 | $5 | $0.85 | $0.5 |
| Context window | 200K | 41K | 131K | 41K |
| 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.