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 | Microsoft | DeepSeek | Moonshot | Zhipu AI |
|---|---|---|---|---|
| Arena ELOHuman preference | Not in our dataset | 1,425 | Not in our dataset | Not in our dataset |
| LiveBench 1.0General reasoning | Not in our dataset | Not in our dataset | 68.4% | Not in our dataset |
| GPQA DiamondScientific knowledge | 69.3% | 79.9% | Not in our dataset | Not in our dataset |
| HLEAcademic reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 14.4% |
| MMLU ProMulti-task understanding | 76.0% | 85.0% | Not in our dataset | 84.6% |
| SimpleBenchCommonsense reasoning | Not in our dataset | Not in our dataset | 57.9% | Not in our dataset |
| AIME 2025Mathematics | 78.0% | 89.3% | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | 67.8% | Not in our dataset | 64.2% |
| LiveCodeBenchCompetitive coding | 53.1% | Not in our dataset | Not in our dataset | Not in our dataset |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 79.7% |
| Terminal-BenchAgentic terminal | Not in our dataset | 39.6% | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | 4.0% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | Phi-4 Reasoning Plus | v3 3.2 | Kimi K2 K2.7 Code | GLM-4 4.5 Thinking |
|---|---|---|---|---|
| Input | $0.07 | $0.26 | $0.6 | $0.6 |
| Output | $0.14 | $0.38 | $3.5 | $2.2 |
| Context window | 16K | 164K | 262K | 131K |
| 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.