Model comparison
Deepseek Coder v2 vs Olmo 7b Instruct
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 10 benchmarks with published results for both. Deepseek Coder v2 scores higher in 6 categories and Olmo 7b Instruct in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Deepseek Coder v2 leads 61.7 to 49.0.
Side by side
| Deepseek Coder v2 | Olmo 7b Instruct | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 35.9 | 30.3 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), Olmo 7b Instruct: 29.6 (#303)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Coding | 1251 | 1016 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), Olmo 7b Instruct: 18.8 (#274)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1207 | 993 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), Olmo 7b Instruct: 30.2 (#237)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Math | 1241 | 1018 |
| GSM8K | 94.5% | — |
Knowledge Not comparable
Deepseek Coder v2: 32.3 (#212), Olmo 7b Instruct: —
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.3 (#240), Olmo 7b Instruct: 24.0 (#291)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Non-English | 1182 | 977 |
| LMArena Chinese | 1201 | 1014 |
| LMArena Russian | 1188 | 947 |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.7 (#242), Olmo 7b Instruct: 49.0 (#301)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Instruction Following | 1180 | 978 |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), Olmo 7b Instruct: —
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.2 (#253), Olmo 7b Instruct: 25.8 (#303)
| Benchmark | Deepseek Coder v2 | Olmo 7b Instruct |
|---|---|---|
| LMArena Text | 1191 | 1032 |
| LMArena Creative Writing | 1120 | 990 |
| LMArena Multi-Turn | 1177 | 1007 |
Frequently asked questions
Is Deepseek Coder v2 better than Olmo 7b Instruct?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 30.3 on the Noometry Index.
Is Deepseek Coder v2 or Olmo 7b Instruct better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 29.6 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Olmo 7b Instruct share?
10 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Olmo 7b Instruct has 10.