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 | Zhipu AI | Moonshot | Mistral AI | MiniMax |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,457 | 1,450 | 1,426 | 1,439 |
| LiveBench 1.0General reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 67.3% |
| GPQA DiamondScientific knowledge | 86.0% | 87.6% | Not in our dataset | 93.0% |
| HLEAcademic reasoning | 30.5% | 31.5% | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | Not in our dataset | 87.1% | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | 53.2% | 46.8% | Not in our dataset | 45.8% |
| AIME 2025Mathematics | 87.1% | 84.8% | 86.3% | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 77.8% | 76.8% | 77.6% | Not in our dataset |
| Terminal-BenchAgentic terminal | 56.2% | 50.8% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 4.9% | 11.8% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | GLM-5 Thinking | Kimi K2 K2.5 Thinking | Mistral Medium 3.5 Thinking | M3 Thinking |
|---|---|---|---|---|
| Input | $1 | $0.5 | $1.5 | $0.3 |
| Output | $3.2 | $2.5 | $7.5 | $1.2 |
| Context window | 205K | 262K | 262K | 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.