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 | Moonshot | Zhipu AI | OpenAI | MiniMax |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,424 | 1,352 | 1,344 |
| GPQA DiamondScientific knowledge | 48.1% | Not in our dataset | Not in our dataset | Not in our dataset |
| HLEAcademic reasoning | Not in our dataset | Not in our dataset | 14.9% | Not in our dataset |
| MMLU ProMulti-task understanding | 69.2% | Not in our dataset | 81.0% | Not in our dataset |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 22.1% | 25.0% |
| Terminal-BenchAgentic terminal | Not in our dataset | 24.5% | 18.7% | 30.0% |
Pricing & context Published USD rates per 1M tokens
| Specification | Kimi K2 Base | GLM-4 4.6 | GPT-OSS 120B Non-thinking | M2 Reasoning |
|---|---|---|---|---|
| Input | $0.57 | $0.5 | $0.03 | $0.255 |
| Output | $2.3 | $2 | $0.136 | $1.02 |
| Context window | 131K | 205K | 131K | 205K |
| 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.