# Claude Sonnet 4.6 vs StarCoder 2 7B

> Claude Sonnet 4.6 has enough public results to be ranked (#50); StarCoder 2 7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/claude-sonnet-4-6-vs-starcoder-2-7b
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Claude Sonnet 4.6 scores higher in 1 category and StarCoder 2 7B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 4.6 leads 46.3 to 34.8.
- StarCoder 2 7B has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 50.3 | 37.0 |
| Rank | 50 | — |
| Context | 1M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Sonnet 4.6: 46.3 (#67)
- StarCoder 2 7B: 34.8

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| LMArena Coding | 1504 | — |
| BigCodeBench Complete | — | 27.7% |
| ALE-Bench | 1,327 | — |
| HumanEval+ | — | 29.9% |

## Agentic & Tool Use

- Claude Sonnet 4.6: 39.1 (#28)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |

## Reasoning

- Claude Sonnet 4.6: 46.1 (#45)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| Epoch Capabilities Index | 152.24 | 93.56 |
| ARC-AGI-2 | 60.4% | — |
| NYT Connections (extended) | 80.9% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| LMArena Hard Prompts | 1484 | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| ForecastBench | 62 | — |
| WinoGrande | — | 57.1% |

## Math

- Claude Sonnet 4.6: 52.9 (#49)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| LMArena Math | 1462 | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
| GSM8K | — | 32.7% |

## Knowledge

- Claude Sonnet 4.6: 51.7 (#65)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
| LMArena Expert | 1500 | — |
| ARC (AI2) Challenge | — | 38.7% |
| MMLU | — | 38.8% |

## Multimodal

- Claude Sonnet 4.6: 38.0 (#68)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |

## Multilingual

- Claude Sonnet 4.6: 54.4 (#41)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1491 | — |
| LMArena French | 1465 | — |
| LMArena German | 1428 | — |
| LMArena Japanese | 1420 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1440 | — |
| LMArena Spanish | 1464 | — |

## Instruction Following

- Claude Sonnet 4.6: 77.4 (#25)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| LMArena Instruction Following | 1475 | — |

## Long Context

- Claude Sonnet 4.6: 45.3 (#44)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| LMArena Longer Query | 1479 | — |

## Writing & Preference

- Claude Sonnet 4.6: 70.2 (#22)
- StarCoder 2 7B: —

| Benchmark | Claude Sonnet 4.6 | StarCoder 2 7B |
|---|---|---|
| LMArena Text | 1458 | — |
| LMArena Creative Writing | 1435 | — |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
| LMArena Multi-Turn | 1464 | — |

## FAQ

### Is Claude Sonnet 4.6 better than StarCoder 2 7B?

Claude Sonnet 4.6 has enough public results to be ranked (#50); StarCoder 2 7B does not yet, so treat this comparison as directional.

### Is Claude Sonnet 4.6 or StarCoder 2 7B better for coding?

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 34.8 in the Noometry coding category.

### How many benchmarks do Claude Sonnet 4.6 and StarCoder 2 7B share?

1 benchmark has published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and StarCoder 2 7B has 7.