Model comparison
StarCoder 2 15B vs Wizardlm 13b
Wizardlm 13b has enough public results to be ranked (#272); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
NVIDIA
MicrosoftSummary
- The widest gap is in coding, where StarCoder 2 15B leads 36.0 to 29.6.
Side by side
| StarCoder 2 15B | Wizardlm 13b | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 37.5 | 30.8 |
| Released | 2024-02-20 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding StarCoder 2 15B leads
StarCoder 2 15B: 36.0, Wizardlm 13b: 29.6 (#293)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Coding | — | 1035 |
| BigCodeBench Complete | 38.4% | — |
| HumanEval+ | 37.8% | — |
Reasoning Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 18.5 (#265)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | — | 1018 |
| Epoch Capabilities Index | 104.61 | — |
| WinoGrande | 64.3% | — |
Math Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 27.8 (#235)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Math | — | 1017 |
| GSM8K | 57.7% | — |
Knowledge Not comparable
StarCoder 2 15B: —, Wizardlm 13b: —
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| ARC (AI2) Challenge | 47.2% | — |
| MMLU | 64.1% | — |
Multilingual Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 27.3 (#272)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | — | 1034 |
| LMArena Chinese | — | 1023 |
Instruction Following Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 53.7 (#280)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | — | 1049 |
Long Context Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 32.0 (#268)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | — | 1054 |
Writing & Preference Not comparable
StarCoder 2 15B: —, Wizardlm 13b: 30.7 (#282)
| Benchmark | StarCoder 2 15B | Wizardlm 13b |
|---|---|---|
| LMArena Text | — | 1077 |
| LMArena Creative Writing | — | 1090 |
| LMArena Multi-Turn | — | 1047 |
Frequently asked questions
Is StarCoder 2 15B better than Wizardlm 13b?
Wizardlm 13b has enough public results to be ranked (#272); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is StarCoder 2 15B or Wizardlm 13b better for coding?
StarCoder 2 15B scores higher on coding benchmarks: 36.0 versus 29.6 in the Noometry coding category.
How many benchmarks do StarCoder 2 15B and Wizardlm 13b share?
0 benchmarks have published results for both models. StarCoder 2 15B has 7 scored results on Noometry and Wizardlm 13b has 10.