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 | Meta | xAI | Qwen | Google |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,489 | 1,455 | 1,474 | 1,485 |
| LiveBench 1.0General reasoning | Not in our dataset | 78.0% | 73.1% | Not in our dataset |
| GPQA DiamondScientific knowledge | 89.5% | Not in our dataset | 90.0% | 91.9% |
| HLEAcademic reasoning | 42.8% | Not in our dataset | Not in our dataset | 37.5% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | Not in our dataset | 90.1% |
| SimpleBenchCommonsense reasoning | Not in our dataset | 75.9% | 70.4% | 76.4% |
| AIME 2025Mathematics | Not in our dataset | Not in our dataset | Not in our dataset | 95.0% |
| GSOGraduate science | Not in our dataset | Not in our dataset | Not in our dataset | 18.6% |
| SWE-Bench VerifiedAgentic coding | 77.4% | Not in our dataset | Not in our dataset | 76.2% |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 85.3% |
| Terminal-BenchAgentic terminal | Not in our dataset | Not in our dataset | Not in our dataset | 54.2% |
| ARC-AGI-2Visual reasoning | 42.5% | 67.1% | Not in our dataset | 84.6% |
Pricing & context Published USD rates per 1M tokens
| Specification | Muse Spark Thinking | Grok 4.6 | Qwen3 Max Qwen 3.7 Max Preview | Gemini 3 Pro 3.0 |
|---|---|---|---|---|
| Input | Not available | $2 | $0.78 | $2 |
| Output | Not available | $6 | $3.9 | $12 |
| Context window | Not available | 500K | 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.