Model comparison
DeepSeek-V2.5 (Sep 2024) vs Olmo 3 32b Think
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 4 categories and Olmo 3 32b Think in 4 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Olmo 3 32b Think leads 38.0 to 31.3.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 37.0 | 38.1 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Olmo 3 32b Think leads
DeepSeek-V2.5 (Sep 2024): 31.3 (#274), Olmo 3 32b Think: 38.0 (#169)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Coding | 1310 | 1318 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Too close to call
DeepSeek-V2.5 (Sep 2024): 24.5 (#145), Olmo 3 32b Think: 24.9 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1302 |
Math Too close to call
DeepSeek-V2.5 (Sep 2024): 33.3 (#177), Olmo 3 32b Think: 33.8 (#165)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Math | 1289 | 1315 |
Knowledge Too close to call
DeepSeek-V2.5 (Sep 2024): 34.2 (#190), Olmo 3 32b Think: 34.4 (#189)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Expert | 1266 | 1272 |
Multilingual DeepSeek-V2.5 (Sep 2024) leads
DeepSeek-V2.5 (Sep 2024): 42.7 (#188), Olmo 3 32b Think: 41.4 (#205)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Non-English | 1273 | 1255 |
| LMArena Chinese | 1317 | 1300 |
| LMArena French | 1288 | 1291 |
| LMArena German | 1258 | 1290 |
| LMArena Russian | 1289 | 1255 |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Too close to call
DeepSeek-V2.5 (Sep 2024): 67.7 (#189), Olmo 3 32b Think: 67.4 (#193)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Instruction Following | 1280 | 1275 |
Long Context Too close to call
DeepSeek-V2.5 (Sep 2024): 39.5 (#169), Olmo 3 32b Think: 39.4 (#177)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Longer Query | 1301 | 1296 |
Writing & Preference Too close to call
DeepSeek-V2.5 (Sep 2024): 50.0 (#182), Olmo 3 32b Think: 49.2 (#188)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Olmo 3 32b Think |
|---|---|---|
| LMArena Text | 1294 | 1300 |
| LMArena Creative Writing | 1285 | 1256 |
| LMArena Multi-Turn | 1297 | 1289 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Olmo 3 32b Think?
Olmo 3 32b Think is the stronger model overall, scoring 38.1 to 37.0 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Olmo 3 32b Think better for coding?
Olmo 3 32b Think scores higher on coding benchmarks: 38.0 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Olmo 3 32b Think share?
14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Olmo 3 32b Think has 14.