Model comparison
Claude Haiku 4.5 vs Grok 4
Grok 4 is the stronger model overall, scoring 48.1 to 39.5 on the Noometry Index.
Last verified . 36 shared benchmarks.
Summary
- They share 36 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Grok 4 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4 leads 36.7 to 15.1.
- The biggest single-benchmark swing is Chess Puzzles: 8% for Claude Haiku 4.5 and 28% for Grok 4.
Side by side
| Claude Haiku 4.5 | Grok 4 | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 39.5 | 48.1 |
| Released | 2025-10-15 | 2025-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | — |
| Max output | 64K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 53 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4 leads
Claude Haiku 4.5: 44.0 (#78), Grok 4: 50.3 (#46)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| WeirdML | 45.4% | 45.7% |
| LMArena Coding | 1453 | 1408 |
| SWE-bench Verified (bash only) | 66.6% | — |
| Aider Polyglot | — | 79.6% |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Claude Haiku 4.5 leads
Claude Haiku 4.5: 33.6 (#52), Grok 4: 32.3 (#68)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| Terminal-Bench | 35.5% | 27.2% |
| Berkeley Function Calling Leaderboard | 68.7% | 63% |
| DeepResearch Bench | 45.5% | 47.3% |
| BALROG | 31.2% | 43.6% |
| GDPval | — | 21.1% |
| Cybench | — | 43% |
| ExploitBench | 13.7% | — |
| LMArena Search | — | 1142 |
| METR Time Horizons | — | 66.6% |
| Vending-Bench 2 | 458.89 | — |
Reasoning Grok 4 leads
Claude Haiku 4.5: 15.1 (#320), Grok 4: 36.7 (#65)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| ARC-AGI-2 | 4% | 16% |
| ARC-AGI-1 | 47.7% | 66.7% |
| Chess Puzzles | 8% | 28% |
| LMArena Hard Prompts | 1420 | 1409 |
| Epoch Capabilities Index | 142.41 | 146.44 |
| ForecastBench | 61.4 | 60.9 |
| SimpleBench | — | 60.5% |
| Kagi LLM Benchmark | — | 73.6% |
| NYT Connections (extended) | 14.3% | — |
| CritPt | 0% | — |
| DTBench | 73.6% | — |
| LMCA | 30.9% | — |
Math Grok 4 leads
Claude Haiku 4.5: 44.9 (#78), Grok 4: 48.4 (#64)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | 84% |
| Omni-MATH | 56.1% | 60.3% |
| LMArena Math | 1396 | 1422 |
| FrontierMath (Feb 2025 set) | 5.9% | 19.7% |
| FrontierMath Tier 4 (v1) | 2.1% | 2.1% |
| MATH Level 5 | 96.4% | — |
Knowledge Grok 4 leads
Claude Haiku 4.5: 37.7 (#153), Grok 4: 53.8 (#55)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| GPQA Diamond | 71.2% | 87% |
| MMLU-Pro | 77.7% | 85.1% |
| GPQA (HELM) | 60.5% | 72.7% |
| LMArena Expert | 1442 | 1415 |
| SimpleQA Verified | 13.2% | — |
| Confabulations | — | 12.4% |
| Vectara Hallucination Rate | 9.8% | — |
Multimodal Grok 4 leads
Claude Haiku 4.5: 26.8 (#118), Grok 4: 33.7 (#94)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| LMArena Vision | — | 1210 |
| GeoBench | — | 45% |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Grok 4 leads
Claude Haiku 4.5: 49.9 (#129), Grok 4: 51.8 (#103)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| LMArena Non-English | 1377 | 1403 |
| LMArena Chinese | 1417 | 1427 |
| LMArena French | 1408 | 1418 |
| LMArena German | 1375 | 1429 |
| LMArena Japanese | 1339 | 1394 |
| LMArena Korean | 1347 | 1377 |
| LMArena Russian | 1381 | 1410 |
| LMArena Spanish | 1420 | 1420 |
Instruction Following Grok 4 leads
Claude Haiku 4.5: 71.4 (#149), Grok 4: 79.2 (#5)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| IFEval | 80.1% | 94.9% |
| LMArena Instruction Following | 1414 | 1387 |
Long Context Grok 4 leads
Claude Haiku 4.5: 43.6 (#92), Grok 4: 63.1 (#4)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| LMArena Longer Query | 1427 | 1409 |
| Fiction.LiveBench | — | 94.4% |
Writing & Preference Too close to call
Claude Haiku 4.5: 57.9 (#123), Grok 4: 58.5 (#116)
| Benchmark | Claude Haiku 4.5 | Grok 4 |
|---|---|---|
| LMArena Text | 1396 | 1411 |
| LMArena Creative Writing | 1372 | 1397 |
| WildBench | 83.9% | 79.7% |
| LMArena Multi-Turn | 1409 | 1416 |
| Short-Story Creative Writing | — | 76.9% |
| EQ-Bench 4 | 1064 | — |
Frequently asked questions
Is Claude Haiku 4.5 better than Grok 4?
Grok 4 is the stronger model overall, scoring 48.1 to 39.5 on the Noometry Index.
Is Claude Haiku 4.5 or Grok 4 better for coding?
Grok 4 scores higher on coding benchmarks: 50.3 versus 44.0 in the Noometry coding category.
How many benchmarks do Claude Haiku 4.5 and Grok 4 share?
36 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Grok 4 has 48.