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 | DeepSeek | Anthropic | Google | Google |
|---|---|---|---|---|
| Arena ELOHuman preference | 1,395 | 1,372 | Not in our dataset | Not in our dataset |
| LiveBench 1.0General reasoning | 72.4% | Not in our dataset | 67.8% | Not in our dataset |
| GPQA DiamondScientific knowledge | 68.4% | 68.0% | 68.2% | 66.7% |
| HLEAcademic reasoning | Not in our dataset | Not in our dataset | Not in our dataset | 6.9% |
| MMLU ProMulti-task understanding | 81.2% | Not in our dataset | 79.4% | Not in our dataset |
| SimpleBenchCommonsense reasoning | 27.2% | 44.9% | Not in our dataset | Not in our dataset |
| AIME 2025Mathematics | 46.7% | Not in our dataset | 46.6% | Not in our dataset |
| GSOGraduate science | Not in our dataset | 3.8% | Not in our dataset | Not in our dataset |
| AiderCode editing | 55.1% | 60.4% | 44.0% | Not in our dataset |
| SWE-Bench VerifiedAgentic coding | 38.8% | Not in our dataset | Not in our dataset | Not in our dataset |
| LiveCodeBenchCompetitive coding | 27.2% | Not in our dataset | Not in our dataset | 34.3% |
| Tau-BenchAgentic tool use | 69.1% | Not in our dataset | 64.3% | Not in our dataset |
| ARC-AGI-2Visual reasoning | Not in our dataset | 0.0% | Not in our dataset | Not in our dataset |
Pricing & context Published USD rates per 1M tokens
| Specification | v3 v3-0324 (Non-thinking) | Claude 3 Sonnet 3.7 | Gemini 2.5 Flash Non-Thinking | Gemini 2.5 Flash-Lite Latest |
|---|---|---|---|---|
| Input | $0.29 | $3 | $0.3 | $0.1 |
| Output | $1.14 | $15 | $2.5 | $0.4 |
| Context window | 164K | 200K | 1.0M | Not available |
| 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.