Model comparison
Mistral Nemo vs StarCoder 2 3B
Mistral Nemo has enough public results to be ranked (#337); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 2 benchmarks with published results for both.
Side by side
| Mistral Nemo | StarCoder 2 3B | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 26.4 | 36.3 |
| Released | 2024-07-01 | 2024-02-22 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 10 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Mistral Nemo: —, StarCoder 2 3B: 33.5
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |
Agentic & Tool Use Not comparable
Mistral Nemo: 23.5 (#125), StarCoder 2 3B: —
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.6% | — |
| BALROG | 17.6% | — |
Reasoning Not comparable
Mistral Nemo: 20.7 (#232), StarCoder 2 3B: —
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 118.68 | 88.76 |
| DTBench | 48.6% | — |
| PIQA | 83.5% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
Mistral Nemo: 25.5 (#268), StarCoder 2 3B: —
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| GSM8K | 84.2% | 21.6% |
| MATH Level 5 | 10.8% | — |
Knowledge Not comparable
Mistral Nemo: 12.3 (#298), StarCoder 2 3B: —
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 29.9% | — |
| ARC (AI2) Challenge | — | 34.2% |
| BoolQ | 82.5% | — |
| MMLU | — | 36.6% |
Writing & Preference Not comparable
Mistral Nemo: 28.5 (#296), StarCoder 2 3B: —
| Benchmark | Mistral Nemo | StarCoder 2 3B |
|---|---|---|
| EQ-Bench Creative Writing | 881 | — |
Frequently asked questions
Is Mistral Nemo better than StarCoder 2 3B?
Mistral Nemo has enough public results to be ranked (#337); StarCoder 2 3B does not yet, so treat this comparison as directional.
How many benchmarks do Mistral Nemo and StarCoder 2 3B share?
2 benchmarks have published results for both models. Mistral Nemo has 10 scored results on Noometry and StarCoder 2 3B has 7.