Model comparison
Gemini 1.5 Pro (May 2024) vs StarCoder 2 3B
Gemini 1.5 Pro (May 2024) has enough public results to be ranked (#261); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 4 shared benchmarks.
Google
NVIDIASummary
- They share 4 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) scores higher in 1 category and StarCoder 2 3B in 0 categories, but none of those gaps is larger than the uncertainty.
- The biggest single-benchmark swing is BigCodeBench Complete: 57.5% for Gemini 1.5 Pro (May 2024) and 21.4% for StarCoder 2 3B.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | StarCoder 2 3B | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 32.1 | 36.3 |
| Released | 2024-02-15 | 2024-02-22 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 45 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemini 1.5 Pro (May 2024): 34.2 (#241), StarCoder 2 3B: 33.5
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 57.5% | 21.4% |
| HumanEval+ | 79.3% | 27.4% |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| LMArena Coding | 1294 | — |
| CadEval | 34% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Not comparable
Gemini 1.5 Pro (May 2024): 12.3 (#338), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 131.73 | 88.76 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| LMArena Hard Prompts | 1296 | — |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| ForecastBench | 58.4 | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Gemini 1.5 Pro (May 2024): 25.8 (#266), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| LMArena Math | 1315 | — |
| MATH Level 5 | 70.4% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
Gemini 1.5 Pro (May 2024): 29.4 (#239), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| MMLU | 86.9% | 36.6% |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| LMArena Expert | 1279 | — |
| ARC (AI2) Challenge | — | 34.2% |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Not comparable
Gemini 1.5 Pro (May 2024): 45.3 (#174), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1312 | — |
| LMArena Chinese | 1331 | — |
| LMArena French | 1302 | — |
| LMArena German | 1286 | — |
| LMArena Japanese | 1292 | — |
| LMArena Korean | 1298 | — |
| LMArena Russian | 1320 | — |
| LMArena Spanish | 1311 | — |
Instruction Following Not comparable
Gemini 1.5 Pro (May 2024): 68.6 (#185), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| IFEval | 83.7% | — |
| LMArena Instruction Following | 1297 | — |
Long Context Not comparable
Gemini 1.5 Pro (May 2024): 39.8 (#169), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1308 | — |
Writing & Preference Not comparable
Gemini 1.5 Pro (May 2024): 52.4 (#172), StarCoder 2 3B: —
| Benchmark | Gemini 1.5 Pro (May 2024) | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1319 | — |
| LMArena Creative Writing | 1333 | — |
| WildBench | 81.3% | — |
| LMArena Multi-Turn | 1296 | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than StarCoder 2 3B?
Gemini 1.5 Pro (May 2024) has enough public results to be ranked (#261); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is Gemini 1.5 Pro (May 2024) or StarCoder 2 3B better for coding?
They score almost the same on coding (34.2 vs 33.5); test both on your own repository before choosing.
How many benchmarks do Gemini 1.5 Pro (May 2024) and StarCoder 2 3B share?
4 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and StarCoder 2 3B has 7.