Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Granite 3.0 2b Instruct
Granite 3.0 2b Instruct has enough public results to be ranked (#286); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Granite 3.0 2b Instruct in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 28.3.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.9% for DeepSeek-V2 (MoE-236B, May 2024) and 20.5% for Granite 3.0 2b Instruct.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 40.3 | 30.8 |
| Released | 2024-05-07 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Granite 3.0 2b Instruct: 28.3 (#316)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.9% | 20.5% |
| LMArena Coding | — | 1090 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 20.5 (#235)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | — | 1073 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 32.2 (#217)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | — | 1117 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 29.0 (#241)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | — | 1064 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 27.0 (#278)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | — | 1033 |
| LMArena Chinese | — | 1070 |
| LMArena Russian | — | 1045 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 53.9 (#284)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1056 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 32.5 (#268)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1070 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Granite 3.0 2b Instruct: 29.6 (#292)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | — | 1080 |
| LMArena Creative Writing | — | 1046 |
| LMArena Multi-Turn | — | 1053 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Granite 3.0 2b Instruct?
Granite 3.0 2b Instruct has enough public results to be ranked (#286); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Granite 3.0 2b Instruct better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 28.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Granite 3.0 2b Instruct share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Granite 3.0 2b Instruct has 13.