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 | Zhipu AI | Moonshot | xAI | Microsoft |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,365 | 1,418 | 1,442 | Not in our dataset |
| LiveBench 1.0General reasoning | Not in our dataset | Not in our dataset | 62.3% | Not in our dataset |
| GPQA DiamondScientific knowledge | Not in our dataset | 74.2% | Not in our dataset | 67.1% |
| HLEAcademic reasoning | 14.4% | Not in our dataset | Not in our dataset | Not in our dataset |
| MMLU ProMulti-task understanding | Not in our dataset | 81.9% | Not in our dataset | 74.3% |
| AIME 2025Mathematics | 91.6% | 51.0% | Not in our dataset | 63.1% |
| SWE-Bench VerifiedAgentic coding | 59.2% | 69.2% | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | Not in our dataset | Not in our dataset | Not in our dataset | 53.8% |
Pricing & context Published USD rates per 1M tokens
| Specification | GLM-4 4.7 Flash | Kimi K2 0905 Preview | Grok 4.3 | Phi-4 Reasoning |
|---|---|---|---|---|
| Input | $0.061 | $0.6 | $1.25 | $0.07 |
| Output | $0.4 | $2.5 | $2.5 | $0.14 |
| Context window | 200K | 262K | 1.0M | 16K |
| 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.