Model comparison
Claude 3.5 Sonnet vs Grok-2 (Dec 2024)
Claude 3.5 Sonnet and Grok-2 (Dec 2024) score almost the same on the Noometry Index (34.4 vs 33.4), so choose on price, context window or the category you care about most.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 6 categories and Grok-2 (Dec 2024) in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude 3.5 Sonnet leads 39.5 to 32.9.
- The biggest single-benchmark swing is LiveBench Coding: 67.1% for Claude 3.5 Sonnet and 46.4% for Grok-2 (Dec 2024).
Side by side
| Claude 3.5 Sonnet | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 34.4 | 33.4 |
| Released | 2024-06-20 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 60 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.5 (#145), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 40% | 22.2% |
| LiveBench Coding | 67.1% | 46.4% |
| LMArena Coding | 1343 | 1288 |
| Aider Polyglot | 51.6% | — |
| GSO | 4.6% | — |
| BigCodeBench Instruct | 46.8% | — |
| BigCodeBench Complete | 58.6% | — |
| CadEval | 48% | — |
| HumanEval+ | 81.7% | — |
| MBPP+ | 74.3% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Sonnet: 32.1 (#61), Grok-2 (Dec 2024): —
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| TheAgentCompany | 24% | — |
| Cybench | 17.5% | — |
| BALROG | 32.6% | — |
| METR Time Horizons | 45.2% | — |
Reasoning Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 22.5 (#176), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 41.4% | 22.7% |
| LiveBench Reasoning | 56.7% | 54.8% |
| LMArena Hard Prompts | 1305 | 1272 |
| DTBench | 67.8% | 65.2% |
| LiveBench Data Analysis | 55% | 54.5% |
| Epoch Capabilities Index | 133.55 | 130.48 |
| LiveBench | 59% | 54.3% |
| EnigmaEval | 0.9% | — |
| ForecastBench | 60.7 | — |
Math Grok-2 (Dec 2024) leads
Claude 3.5 Sonnet: 18.0 (#282), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 11.5% |
| LiveBench Math | 52.3% | 54.9% |
| LMArena Math | 1306 | 1283 |
| MATH Level 5 | 56.9% | 63.5% |
| FrontierMath (Feb 2025 set) | 2.1% | 0.7% |
| Omni-MATH | 27.6% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok-2 (Dec 2024) leads
Claude 3.5 Sonnet: 28.5 (#236), Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 55.3% | 53.8% |
| Confabulations | 19.9% | 20.1% |
| LMArena Expert | 1264 | 1254 |
| Humanity's Last Exam | 4.1% | — |
| MMLU-Pro | 77.7% | — |
| GPQA (HELM) | 56.5% | — |
| MMLU | 87.3% | — |
Multimodal Not comparable
Claude 3.5 Sonnet: 26.0 (#115), Grok-2 (Dec 2024): —
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1125 | — |
| Video-MME | 60% | — |
| GeoBench | 62% | — |
| VPCT | 33% | — |
Multilingual Too close to call
Claude 3.5 Sonnet: 43.4 (#180), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1283 | 1282 |
| LMArena Chinese | 1271 | 1289 |
| LMArena French | 1304 | 1317 |
| LMArena German | 1297 | 1287 |
| LMArena Japanese | 1234 | 1244 |
| LMArena Korean | 1200 | 1237 |
| LMArena Russian | 1305 | 1286 |
| LMArena Spanish | 1289 | 1281 |
Instruction Following Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 69.0 (#177), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LiveBench Instruction Following | 69.3% | 69.6% |
| LMArena Instruction Following | 1297 | 1270 |
| IFEval | 85.5% | — |
Long Context Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 39.9 (#162), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1311 | 1276 |
Writing & Preference Claude 3.5 Sonnet leads
Claude 3.5 Sonnet: 53.0 (#159), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | Claude 3.5 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1298 | 1305 |
| LMArena Creative Writing | 1292 | 1284 |
| Short-Story Creative Writing | 80.3% | 63.6% |
| LMArena Multi-Turn | 1326 | 1290 |
| LiveBench Language | 53.8% | 45.6% |
| EQ-Bench Creative Writing | 1451 | — |
| WildBench | 79.2% | — |
Frequently asked questions
Is Claude 3.5 Sonnet better than Grok-2 (Dec 2024)?
Claude 3.5 Sonnet and Grok-2 (Dec 2024) score almost the same on the Noometry Index (34.4 vs 33.4), so choose on price, context window or the category you care about most.
Is Claude 3.5 Sonnet or Grok-2 (Dec 2024) better for coding?
Claude 3.5 Sonnet scores higher on coding benchmarks: 39.5 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Sonnet and Grok-2 (Dec 2024) share?
34 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Grok-2 (Dec 2024) has 34.