Compare models. Find the differences.
Add, remove, or change models in the table.
Benchmark snapshot
2 benchmarks in common.
4 models selected. 2 benchmarks in common.
Reported scores; test settings may differ.
| Benchmark | OpenAI | Google | Moonshot | DeepSeek |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,475 | 1,478 | 1,488 | 1,439 |
| LiveBench 1.0General reasoning | 78.0% | 74.6% | 79.2% | Not in our dataset |
| GPQA DiamondScientific knowledge | 92.8% | Not in our dataset | Not in our dataset | 88.1% |
| HLEAcademic reasoning | 43.9% | 40.2% | Not in our dataset | 34.8% |
| MMLU ProMulti-task understanding | Not in our dataset | Not in our dataset | Not in our dataset | 86.2% |
| SimpleBenchCommonsense reasoning | Not in our dataset | 76.7% | 60.7% | Not in our dataset |
| GSOGraduate science | 31.4% | Not in our dataset | Not in our dataset | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | Not in our dataset | Not in our dataset | Not in our dataset | 79.0% |
| LiveCodeBenchCompetitive coding | Not in our dataset | Not in our dataset | Not in our dataset | 91.6% |
| Tau-BenchAgentic tool use | Not in our dataset | Not in our dataset | Not in our dataset | 89.1% |
| Terminal-BenchAgentic terminal | 75.1% | Not in our dataset | Not in our dataset | Not in our dataset |
| ARC-AGI-2Visual reasoning | 74.0% | 72.1% | 60.4% | 61.4% |
Pricing & context Published USD rates per 1M tokens
| Specification | GPT-5.4 Thinking | Gemini 3.5 Flash | Kimi K3 Thinking | V4 Flash Thinking |
|---|---|---|---|---|
| Input | $2.5 | $1.5 | $0.192 | $0.091 |
| Output | $15 | $9 | $16 | $0.182 |
| Context window | 1.1M | 1.0M | 1.0M | 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.