Model comparison
DeepSeek V4 Flash vs Dolly 2.0-12b
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 25.5 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
DatabricksSummary
- They share 10 benchmarks with published results for both. DeepSeek V4 Flash scores higher in 6 categories and Dolly 2.0-12b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek V4 Flash leads 63.8 to 15.2.
Side by side
| DeepSeek V4 Flash | Dolly 2.0-12b | |
|---|---|---|
| Provider | DeepSeek | Databricks |
| Noometry Index | 53.6 | 25.5 |
| Released | 2026-04-24 | 2023-04-11 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 41 | 17 |
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), Dolly 2.0-12b: 23.4 (#332)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Coding | 1457 | 776 |
| 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), Dolly 2.0-12b: 15.3 (#316)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Hard Prompts | 1444 | 804 |
| Epoch Capabilities Index | 154.49 | 89.67 |
| 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% | — |
| HellaSwag | — | 70.8% |
| PIQA | — | 75.4% |
| WinoGrande | — | 61.8% |
Math DeepSeek V4 Flash leads
DeepSeek V4 Flash: 60.3 (#37), Dolly 2.0-12b: 27.3 (#251)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Math | 1427 | 871 |
| 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% | — |
Knowledge Not comparable
DeepSeek V4 Flash: 55.4 (#48), Dolly 2.0-12b: —
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| GPQA Diamond | 91% | — |
| SimpleQA Verified | 33.6% | — |
| LMArena Expert | 1441 | — |
| ARC (AI2) Challenge | — | 39.6% |
| BoolQ | — | 56.3% |
| MMLU | — | 26.2% |
| OpenBookQA | — | 39.2% |
Multilingual DeepSeek V4 Flash leads
DeepSeek V4 Flash: 53.0 (#72), Dolly 2.0-12b: 17.4 (#296)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Non-English | 1420 | 836 |
| LMArena Chinese | 1468 | 836 |
| LMArena French | 1439 | — |
| LMArena German | 1418 | — |
| LMArena Japanese | 1406 | — |
| LMArena Korean | 1384 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1436 | — |
Instruction Following DeepSeek V4 Flash leads
DeepSeek V4 Flash: 74.9 (#81), Dolly 2.0-12b: 38.7 (#304)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Instruction Following | 1421 | 814 |
Long Context Not comparable
DeepSeek V4 Flash: 43.8 (#85), Dolly 2.0-12b: —
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Longer Query | 1434 | — |
Writing & Preference DeepSeek V4 Flash leads
DeepSeek V4 Flash: 63.8 (#61), Dolly 2.0-12b: 15.2 (#311)
| Benchmark | DeepSeek V4 Flash | Dolly 2.0-12b |
|---|---|---|
| LMArena Text | 1432 | 851 |
| LMArena Creative Writing | 1403 | 864 |
| LMArena Multi-Turn | 1449 | 740 |
| EQ-Bench Creative Writing | 1559 | — |
Frequently asked questions
Is DeepSeek V4 Flash better than Dolly 2.0-12b?
DeepSeek V4 Flash is the stronger model overall, scoring 53.6 to 25.5 on the Noometry Index.
Is DeepSeek V4 Flash or Dolly 2.0-12b better for coding?
DeepSeek V4 Flash scores higher on coding benchmarks: 47.9 versus 23.4 in the Noometry coding category.
How many benchmarks do DeepSeek V4 Flash and Dolly 2.0-12b share?
10 benchmarks have published results for both models. DeepSeek V4 Flash has 41 scored results on Noometry and Dolly 2.0-12b has 17.