Model comparison
Claude Sonnet 5 vs StarCoder 2 3B
Claude Sonnet 5 has enough public results to be ranked (#29); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. Claude Sonnet 5 scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Claude Sonnet 5 leads 55.5 to 33.5.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 5 | StarCoder 2 3B | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 54.6 | 36.3 |
| Released | 2026-06-29 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 51 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 5 leads
Claude Sonnet 5: 55.5 (#26), StarCoder 2 3B: 33.5
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| DeepSWE | 53.8% | — |
| FrontierCode | 42.7% | — |
| CursorBench | 34.1% | — |
| LMArena WebDev | 1541 | — |
| SciCode | 54.3% | — |
| GSO | 37.3% | — |
| WeirdML | 68.8% | — |
| LMArena Coding | 1483 | — |
| BigCodeBench Complete | — | 21.4% |
| ALE-Bench | 1,463 | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Claude Sonnet 5: 42.8 (#18), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| APEX-Agents | 54.5% | — |
| GBAEval | 65.3% | — |
| LMArena Search | 1194 | — |
| Vending-Bench 2 | 6,378 | — |
Reasoning Not comparable
Claude Sonnet 5: 49.1 (#39), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 156.21 | 88.76 |
| SimpleBench | 60.6% | — |
| NYT Connections (extended) | 75.1% | — |
| CritPt | 16.9% | — |
| Chess Puzzles | 35% | — |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 35% | — |
| DTBench | 92.5% | — |
| LMCA | 50% | — |
| Surface Evolver Bench | 60% | — |
| Bench to the Future 3 | 0.14 | — |
| ForecastBench | 61.1 | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Claude Sonnet 5: 66.2 (#27), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 65.6% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 94.7% | — |
| ProofBench | 77% | — |
| LMArena Math | 1467 | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Claude Sonnet 5: 55.6 (#47), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 90.5% | — |
| SimpleQA Verified | 33.7% | — |
| LMArena Expert | 1490 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Multimodal Not comparable
Claude Sonnet 5: 42.4 (#31), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1274 | — |
| Blueprint-Bench 2 | 24.9% | — |
| LMArena Document | 1466 | — |
Multilingual Not comparable
Claude Sonnet 5: 53.8 (#55), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1477 | — |
| LMArena French | 1460 | — |
| LMArena German | 1440 | — |
| LMArena Japanese | 1422 | — |
| LMArena Korean | 1411 | — |
| LMArena Russian | 1451 | — |
| LMArena Spanish | 1437 | — |
Instruction Following Not comparable
Claude Sonnet 5: 76.3 (#41), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1452 | — |
Long Context Not comparable
Claude Sonnet 5: 44.8 (#55), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1463 | — |
Writing & Preference Not comparable
Claude Sonnet 5: 69.2 (#25), StarCoder 2 3B: —
| Benchmark | Claude Sonnet 5 | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1442 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1794 | — |
| EQ-Bench 4 | 1236 | — |
| LMArena Multi-Turn | 1454 | — |
Frequently asked questions
Is Claude Sonnet 5 better than StarCoder 2 3B?
Claude Sonnet 5 has enough public results to be ranked (#29); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Claude Sonnet 5 or StarCoder 2 3B better for coding?
Claude Sonnet 5 scores higher on coding benchmarks: 55.5 versus 33.5 in the Noometry coding category.
How many benchmarks do Claude Sonnet 5 and StarCoder 2 3B share?
1 benchmark has published results for both models. Claude Sonnet 5 has 51 scored results on Noometry and StarCoder 2 3B has 7.