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 | Anthropic | Qwen | xAI | Anthropic |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,474 | Not in our dataset | 1,465 | 1,472 |
| LiveBench 1.0General reasoning | 72.6% | Not in our dataset | 75.8% | 73.0% |
| GPQA DiamondScientific knowledge | 87.0% | Not in our dataset | Not in our dataset | 89.9% |
| HLEAcademic reasoning | 30.8% | 25.3% | Not in our dataset | 33.2% |
| MMLU ProMulti-task understanding | 89.5% | 86.7% | Not in our dataset | Not in our dataset |
| SimpleBenchCommonsense reasoning | 62.0% | Not in our dataset | 70.0% | Not in our dataset |
| AIME 2025Mathematics | 92.8% | Not in our dataset | Not in our dataset | 86.9% |
| SWE-Bench VerifiedAgentic coding | 80.9% | Not in our dataset | Not in our dataset | 79.6% |
| Tau-BenchAgentic tool use | 88.9% | Not in our dataset | Not in our dataset | 91.7% |
| Terminal-BenchAgentic terminal | 59.3% | Not in our dataset | Not in our dataset | 59.1% |
| ARC-AGI-2Visual reasoning | 37.6% | Not in our dataset | 52.6% | 58.3% |
Pricing & context Published USD rates per 1M tokens
| Specification | Claude Opus 4 4.5 Thinking | 3.5 122B A10B Non-Thinking | Grok 4.5 | Claude Sonnet 4 4.6 Thinking |
|---|---|---|---|---|
| Input | $5 | $0.26 | $2 | $3 |
| Output | $25 | $2.08 | $6 | $15 |
| Context window | 200K | 262K | 2.0M | 200K |
| 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.