Model comparison
DeepSeek V4 Flash vs Olmo 2 0325 32b Instruct
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 32.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 8 categories and Olmo 2 0325 32b Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek V4 Flash leads 55.4 to 19.5.
Side by side
| DeepSeek V4 Flash | Olmo 2 0325 32b Instruct | |
|---|---|---|
| Provider | DeepSeek | Allen Institute for AI (Ai2) |
| Noometry Index | 53.6 | 32.7 |
| Released | 2026-04-24 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Flash leads
DeepSeek V4 Flash: 47.9 (#59), Olmo 2 0325 32b Instruct: 35.2 (#227)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Coding | 1457 | 1210 |
| FrontierCode | 18.8% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 49.9% | — |
| WeirdML | 63% | — |
| ALE-Bench | 1,306 | — |
Reasoning DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.7 (#30), Olmo 2 0325 32b Instruct: 23.6 (#175)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1444 | 1208 |
| ARC-AGI-2 | 61.4% | — |
| SimpleBench | 61.1% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | 89% | — |
| CritPt | 16.6% | — |
| Chess Puzzles | 33% | — |
| Mystery Game Puzzles | 34% | — |
| DTBench | 90.9% | — |
| LMCA | 41.7% | — |
| Epoch Capabilities Index | 154.49 | — |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Olmo 2 0325 32b Instruct: 26.8 (#255)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Math | 1427 | 1208 |
| FrontierMath (Tiers 1-3) | 57.5% | — |
| FrontierMath Tier 4 | 24.4% | — |
| MathArena Final-Answer Competitions | 76.5% | — |
| OTIS Mock AIME 2024-2025 | 94.4% | — |
| ProofBench | 56% | — |
| Omni-MATH | — | 16.1% |
Knowledge DeepSeek V4 Flash leads
DeepSeek V4 Flash: 55.4 (#48), Olmo 2 0325 32b Instruct: 19.5 (#279)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| MMLU-Pro | — | 41.4% |
| GPQA (HELM) | — | 28.7% |
| LMArena Expert | 1441 | — |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Olmo 2 0325 32b Instruct: 34.8 (#248)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Non-English | 1420 | 1160 |
| LMArena Chinese | 1468 | 1192 |
| LMArena Russian | 1428 | 1187 |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Spanish | 1436 | — |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Olmo 2 0325 32b Instruct: 61.5 (#244)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Instruction Following | 1421 | 1186 |
| IFEval | — | 78% |
Long Context DeepSeek V4 Flash leads
DeepSeek V4 Flash: 43.8 (#85), Olmo 2 0325 32b Instruct: 36.2 (#234)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Longer Query | 1434 | 1194 |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Olmo 2 0325 32b Instruct: 42.1 (#236)
| Benchmark | DeepSeek V4 Flash | Olmo 2 0325 32b Instruct |
|---|---|---|
| LMArena Text | 1432 | 1218 |
| LMArena Creative Writing | 1403 | 1199 |
| LMArena Multi-Turn | 1449 | 1221 |
| EQ-Bench Creative Writing | 1559 | — |
| WildBench | — | 73.4% |
Frequently asked questions
Is DeepSeek V4 Flash better than Olmo 2 0325 32b Instruct?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 32.7 on the Noometry Index.
Is DeepSeek V4 Flash or Olmo 2 0325 32b Instruct better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 35.2 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Olmo 2 0325 32b Instruct share?
11 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Olmo 2 0325 32b Instruct has 16.