Model comparison
Grok 4.5 vs StarCoder 2 15B
Grok 4.5 has enough public results to be ranked (#25); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
NVIDIASummary
- They share 1 benchmark with published results for both. Grok 4.5 scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Grok 4.5 leads 52.2 to 36.6.
- StarCoder 2 15B has downloadable open weights; the other is API-only.
Side by side
| Grok 4.5 | StarCoder 2 15B | |
|---|---|---|
| Provider | xAI | NVIDIA |
| Noometry Index | 55.0 | 38.1 |
| Released | 2026-07-08 | 2024-02-20 |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 52 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.5 leads
Grok 4.5: 52.2 (#35), StarCoder 2 15B: 36.6
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| DeepSWE | 53.8% | — |
| FrontierCode | 42.4% | — |
| LMArena WebDev | 1553 | — |
| SciCode | 54.1% | — |
| WeirdML | 46.4% | — |
| LMArena Coding | 1474 | — |
| BigCodeBench Complete | — | 38.4% |
| ALE-Bench | 1,309 | — |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
Grok 4.5: 44.4 (#17), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| APEX-Agents | 56.2% | — |
| τ²-bench Banking | 47.9% | — |
| PostTrainBench | 23.4% | — |
| GBAEval | 65.4% | — |
| GDP.pdf | 14% | — |
| LMArena Search | 1213 | — |
| Vending-Bench 2 | 3,887 | — |
Reasoning Not comparable
Grok 4.5: 56.1 (#25), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 153.92 | 105 |
| ARC-AGI-2 | 52.6% | — |
| SimpleBench | 70% | — |
| Kagi LLM Benchmark | 83.5% | — |
| NYT Connections (extended) | 79.9% | — |
| ARC-AGI-1 | 87.2% | — |
| CritPt | 15.4% | — |
| Chess Puzzles | 36% | — |
| LMArena Hard Prompts | 1462 | — |
| DTBench | 96.5% | — |
| LMCA | 45.2% | — |
| Surface Evolver Bench | 74.4% | — |
| WinoGrande | — | 64.3% |
Math Not comparable
Grok 4.5: 60.9 (#35), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 24.4% | — |
| OTIS Mock AIME 2024-2025 | 97.8% | — |
| ProofBench | 31% | — |
| LMArena Math | 1459 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Grok 4.5: 62.3 (#24), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 93.4% | — |
| SimpleQA Verified | 48.3% | — |
| LMArena Expert | 1466 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multimodal Not comparable
Grok 4.5: 37.6 (#72), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| LMArena Vision | 1288 | — |
| Blueprint-Bench 2 | 27.3% | — |
| Furniture Assembly | 22.5% | — |
| LMArena Document | 1452 | — |
Multilingual Not comparable
Grok 4.5: 54.4 (#42), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1496 | — |
| LMArena French | 1456 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1428 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1448 | — |
| LMArena Spanish | 1450 | — |
Instruction Following Not comparable
Grok 4.5: 76.0 (#48), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1446 | — |
Long Context Not comparable
Grok 4.5: 44.8 (#56), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1463 | — |
Writing & Preference Not comparable
Grok 4.5: 65.8 (#42), StarCoder 2 15B: —
| Benchmark | Grok 4.5 | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1448 | — |
| LMArena Creative Writing | 1442 | — |
| EQ-Bench Creative Writing | 1579 | — |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is Grok 4.5 better than StarCoder 2 15B?
Grok 4.5 has enough public results to be ranked (#25); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Grok 4.5 or StarCoder 2 15B better for coding?
Grok 4.5 scores higher on coding benchmarks: 52.2 versus 36.6 in the Noometry coding category.
How many benchmarks do Grok 4.5 and StarCoder 2 15B share?
1 benchmark has published results for both models. Grok 4.5 has 52 scored results on Noometry and StarCoder 2 15B has 7.