Model comparison
Claude 3 Sonnet vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 28.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. Claude 3 Sonnet scores higher in 1 category and Grok-2 (Dec 2024) in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok-2 (Dec 2024) leads 19.6 to 10.0.
- The biggest single-benchmark swing is MATH Level 5: 18.2% for Claude 3 Sonnet and 63.5% for Grok-2 (Dec 2024).
Side by side
| Claude 3 Sonnet | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 28.8 | 33.4 |
| Released | 2024-02-29 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 29.2 (#296), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 10.2% | 22.2% |
| LMArena Coding | 1223 | 1288 |
| BigCodeBench Instruct | 42.7% | — |
| LiveBench Coding | — | 46.4% |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Reasoning Claude 3 Sonnet leads
Claude 3 Sonnet: 19.7 (#232), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1272 |
| DTBench | 53.6% | 65.2% |
| Epoch Capabilities Index | 120.69 | 130.48 |
| SimpleBench | — | 22.7% |
| LiveBench Reasoning | — | 54.8% |
| LiveBench Data Analysis | — | 54.5% |
| LiveBench | — | 54.3% |
| WinoGrande | 75.1% | — |
Math Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 10.0 (#305), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.5% | 11.5% |
| LMArena Math | 1213 | 1283 |
| MATH Level 5 | 18.2% | 63.5% |
| LiveBench Math | — | 54.9% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 21.1 (#271), Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 40.6% | 53.8% |
| LMArena Expert | 1173 | 1254 |
| Confabulations | — | 20.1% |
| MMLU | 75.9% | — |
Multimodal Not comparable
Claude 3 Sonnet: 24.7 (#120), Grok-2 (Dec 2024): —
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 984 | — |
Multilingual Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 38.0 (#229), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1205 | 1282 |
| LMArena Chinese | 1188 | 1289 |
| LMArena French | 1228 | 1317 |
| LMArena German | 1204 | 1287 |
| LMArena Japanese | 1131 | 1244 |
| LMArena Korean | 1128 | 1237 |
| LMArena Russian | 1227 | 1286 |
| LMArena Spanish | 1204 | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 63.1 (#230), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1200 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 36.7 (#223), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1211 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
Claude 3 Sonnet: 42.3 (#233), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | Claude 3 Sonnet | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1218 | 1305 |
| LMArena Creative Writing | 1186 | 1284 |
| LMArena Multi-Turn | 1227 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Claude 3 Sonnet better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 28.8 on the Noometry Index.
Is Claude 3 Sonnet or Grok-2 (Dec 2024) better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 32.9 versus 29.2 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Grok-2 (Dec 2024) share?
23 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok-2 (Dec 2024) has 34.