Model comparison
Claude Opus 4.8 vs Grok-2 (Dec 2024)
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 33.4 on the Noometry Index.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude Opus 4.8 scores higher in 8 categories and Grok-2 (Dec 2024) in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 4.8 leads 78.2 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 98.3% for Claude Opus 4.8 and 11.5% for Grok-2 (Dec 2024).
Side by side
| Claude Opus 4.8 | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 60.7 | 33.4 |
| Released | 2026-05-28 | 2024-08-13 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $5 | — |
| Output $ / M tokens | $25 | — |
| Results tracked | 65 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4.8 leads
Claude Opus 4.8: 60.2 (#9), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| WeirdML | 82.9% | 22.2% |
| LMArena Coding | 1491 | 1288 |
| DeepSWE | 59% | — |
| FrontierCode | 46.5% | — |
| LMArena WebDev | 1556 | — |
| SciCode | 53.5% | — |
| GSO | 47.1% | — |
| LiveBench Coding | — | 46.4% |
| ALE-Bench | 1,564 | — |
Agentic & Tool Use Not comparable
Claude Opus 4.8: 47.6 (#10), Grok-2 (Dec 2024): —
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| APEX-Agents | 48.9% | — |
| OSWorld 2.0 | 20.6% | — |
| Remote Labor Index | 8.3% | — |
| τ²-bench Banking | 39.7% | — |
| DeepResearch Bench | 50.2% | — |
| PostTrainBench | 33.8% | — |
| GBAEval | 70.9% | — |
| GDP.pdf | 24% | — |
| LMArena Search | 1204 | — |
| Vending-Bench 2 | 5,787 | — |
Reasoning Claude Opus 4.8 leads
Claude Opus 4.8: 64.6 (#14), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| SimpleBench | 64.8% | 22.7% |
| LMArena Hard Prompts | 1481 | 1272 |
| DTBench | 94.9% | 65.2% |
| Epoch Capabilities Index | 158.3 | 130.48 |
| ARC-AGI-2 | 72.1% | — |
| Kagi LLM Benchmark | 88.8% | — |
| NYT Connections (extended) | 91.1% | — |
| ARC-AGI-1 | 92.5% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 34% | — |
| EnigmaEval | 23.5% | — |
| EBR-Bench | 28.6% | — |
| LiveBench Reasoning | — | 54.8% |
| Mystery Game Puzzles | 36% | — |
| LiveBench Data Analysis | — | 54.5% |
| LMCA | 57.5% | — |
| Surface Evolver Bench | 87.5% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 59.9 | — |
| LiveBench | — | 54.3% |
Math Claude Opus 4.8 leads
Claude Opus 4.8: 78.2 (#11), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.3% | 11.5% |
| LMArena Math | 1487 | 1283 |
| FrontierMath (Feb 2025 set) | 47.2% | 0.7% |
| FrontierMath (Tiers 1-3) | 80% | — |
| FrontierMath Tier 4 | 56.1% | — |
| MathArena Final-Answer Competitions | 91.8% | — |
| ProofBench | 69% | — |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Claude Opus 4.8 leads
Claude Opus 4.8: 61.3 (#26), Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | 91% | 53.8% |
| LMArena Expert | 1501 | 1254 |
| SimpleQA Verified | 53% | — |
| Confabulations | — | 20.1% |
Multimodal Not comparable
Claude Opus 4.8: 43.2 (#20), Grok-2 (Dec 2024): —
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Vision | 1295 | — |
| Blueprint-Bench 2 | 14.5% | — |
| Furniture Assembly | 42.5% | — |
| LMArena Document | 1475 | — |
Multilingual Claude Opus 4.8 leads
Claude Opus 4.8: 55.4 (#31), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1450 | 1282 |
| LMArena Chinese | 1509 | 1289 |
| LMArena French | 1482 | 1317 |
| LMArena German | 1470 | 1287 |
| LMArena Japanese | 1440 | 1244 |
| LMArena Korean | 1432 | 1237 |
| LMArena Russian | 1476 | 1286 |
| LMArena Spanish | 1470 | 1281 |
Instruction Following Claude Opus 4.8 leads
Claude Opus 4.8: 77.6 (#22), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1476 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Claude Opus 4.8 leads
Claude Opus 4.8: 45.4 (#37), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1482 | 1276 |
Writing & Preference Claude Opus 4.8 leads
Claude Opus 4.8: 72.1 (#17), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | Claude Opus 4.8 | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1460 | 1305 |
| LMArena Creative Writing | 1453 | 1284 |
| LMArena Multi-Turn | 1476 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| EQ-Bench Creative Writing | 1840 | — |
| EQ-Bench 4 | 1281 | — |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Claude Opus 4.8 better than Grok-2 (Dec 2024)?
Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 33.4 on the Noometry Index.
Is Claude Opus 4.8 or Grok-2 (Dec 2024) better for coding?
Claude Opus 4.8 scores higher on coding benchmarks: 60.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude Opus 4.8 and Grok-2 (Dec 2024) share?
24 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Grok-2 (Dec 2024) has 34.