Model comparison
Gemini 2.0 Flash (Feb 2025) vs StarCoder 2 3B
Gemini 2.0 Flash (Feb 2025) has enough public results to be ranked (#228); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Google
NVIDIASummary
- They share 3 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and StarCoder 2 3B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where StarCoder 2 3B leads 33.5 to 28.4.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.9% for Gemini 2.0 Flash (Feb 2025) and 21.4% for StarCoder 2 3B.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 35.1 | 36.3 |
| Released | 2024-12-06 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 54 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 3B leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), StarCoder 2 3B: 33.5
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 59.9% | 21.4% |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| LMArena Coding | 1350 | — |
| CadEval | 30% | — |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Not comparable
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 135.36 | 88.76 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| LMArena Hard Prompts | 1346 | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| LiveBench | 66.9% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| LMArena Math | 1352 | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| MMLU | 79.7% | 36.6% |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| LMArena Expert | 1339 | — |
| ARC (AI2) Challenge | — | 34.2% |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Not comparable
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1342 | — |
| LMArena Chinese | 1373 | — |
| LMArena French | 1391 | — |
| LMArena German | 1353 | — |
| LMArena Japanese | 1294 | — |
| LMArena Korean | 1313 | — |
| LMArena Russian | 1351 | — |
| LMArena Spanish | 1363 | — |
Instruction Following Not comparable
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
| LMArena Instruction Following | 1336 | — |
Long Context Not comparable
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| Fiction.LiveBench | 61.1% | — |
| LMArena Longer Query | 1344 | — |
Writing & Preference Not comparable
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), StarCoder 2 3B: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1354 | — |
| LMArena Creative Writing | 1340 | — |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
| LMArena Multi-Turn | 1350 | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than StarCoder 2 3B?
Gemini 2.0 Flash (Feb 2025) has enough public results to be ranked (#228); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Gemini 2.0 Flash (Feb 2025) or StarCoder 2 3B better for coding?
StarCoder 2 3B scores higher on coding benchmarks: 33.5 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and StarCoder 2 3B share?
3 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and StarCoder 2 3B has 7.