Model comparison
DeepSeek-V2.5 (Sep 2024) vs Granite 3.0 2b Instruct
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.2 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 8 categories and Granite 3.0 2b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 50.0 to 29.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 48.6% for DeepSeek-V2.5 (Sep 2024) and 20.5% for Granite 3.0 2b Instruct.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 37.0 | 30.2 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Granite 3.0 2b Instruct: 27.8 (#311)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| BigCodeBench Instruct | 48.6% | 20.5% |
| LMArena Coding | 1310 | 1090 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Granite 3.0 2b Instruct: 19.6 (#234)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1073 |
Math DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Granite 3.0 2b Instruct: 29.7 (#215)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | 1289 | 1117 |
Knowledge DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Granite 3.0 2b Instruct: 28.4 (#238)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | 1266 | 1064 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Granite 3.0 2b Instruct: 27.1 (#273)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | 1273 | 1033 |
| LMArena Chinese | 1317 | 1070 |
| LMArena Russian | 1289 | 1045 |
| LMArena French | 1288 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Granite 3.0 2b Instruct: 54.2 (#279)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1280 | 1056 |
Long Context DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Granite 3.0 2b Instruct: 32.5 (#263)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1301 | 1071 |
Writing & Preference DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Granite 3.0 2b Instruct: 29.8 (#287)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | 1294 | 1080 |
| LMArena Creative Writing | 1285 | 1046 |
| LMArena Multi-Turn | 1297 | 1053 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Granite 3.0 2b Instruct?
DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.0 to 30.2 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Granite 3.0 2b Instruct better for coding?
DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.3 versus 27.8 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Granite 3.0 2b Instruct share?
13 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Granite 3.0 2b Instruct has 13.