Model comparison
Dolly 2.0-12b vs GPT-5.4
GPT-5.4 is the stronger model overall, scoring 59.5 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
DatabricksSummary
- They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and GPT-5.4 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 leads 72.1 to 15.3.
- Dolly 2.0-12b has downloadable open weights; the other is API-only.
Side by side
| Dolly 2.0-12b | GPT-5.4 | |
|---|---|---|
| Provider | Databricks | OpenAI |
| Noometry Index | 24.9 | 59.5 |
| Released | 2023-04-11 | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $15 |
| Results tracked | 17 | 68 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 leads
Dolly 2.0-12b: 23.0 (#327), GPT-5.4: 52.8 (#28)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Coding | 776 | 1497 |
| SWE-bench Verified | — | 76.9% |
| DeepSWE | — | 51.8% |
| LMArena WebDev | — | 1465 |
| SciCode | — | 56.6% |
| GSO | — | 31.4% |
| WeirdML | — | 77.7% |
| MirrorCode | — | 15.6% |
| ALE-Bench | — | 1,607 |
| AlgoTune | — | 1.85 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, GPT-5.4: 46.5 (#12)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| Terminal-Bench | — | 81.8% |
| APEX-Agents | — | 52.4% |
| τ²-bench Banking | — | 39.4% |
| DeepResearch Bench | — | 35.1% |
| PostTrainBench | — | 19% |
| GBAEval | — | 45.1% |
| LMArena Search | — | 1197 |
| METR Time Horizons | — | 74.3% |
| Vending-Bench 2 | — | 6,144 |
Reasoning GPT-5.4 leads
Dolly 2.0-12b: 14.6 (#315), GPT-5.4: 61.7 (#17)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1485 |
| Epoch Capabilities Index | 88.94 | 156.92 |
| ARC-AGI-2 | — | 74% |
| Kagi LLM Benchmark | — | 63.8% |
| NYT Connections (extended) | — | 91.3% |
| ARC-AGI-1 | — | 93.7% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 44% |
| EnigmaEval | — | 16% |
| Thematic Generalization | — | 80% |
| EBR-Bench | — | 25.4% |
| Mystery Game Puzzles | — | 37% |
| DTBench | — | 94.4% |
| LMCA | — | 52% |
| ForecastBench | — | 59.5 |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math GPT-5.4 leads
Dolly 2.0-12b: 25.0 (#250), GPT-5.4: 73.3 (#14)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Math | 871 | 1488 |
| FrontierMath (Tiers 1-3) | — | 78.6% |
| FrontierMath Tier 4 | — | 49% |
| MathArena Final-Answer Competitions | — | 83.1% |
| OTIS Mock AIME 2024-2025 | — | 97.8% |
| ProofBench | — | 56% |
| FrontierMath (Feb 2025 set) | — | 47.6% |
| FrontierMath Tier 4 (v1) | — | 27.1% |
Knowledge Not comparable
Dolly 2.0-12b: —, GPT-5.4: 65.3 (#13)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| GPQA Diamond | — | 93.3% |
| Humanity's Last Exam | — | 36.2% |
| SimpleQA Verified | — | 45.1% |
| Vectara Hallucination Rate | — | 7% |
| LMArena Expert | — | 1507 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multimodal Not comparable
Dolly 2.0-12b: —, GPT-5.4: 43.8 (#19)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Vision | — | 1302 |
| Blueprint-Bench 2 | — | 27.1% |
| Furniture Assembly | — | 37.5% |
| LMArena Document | — | 1471 |
Multilingual GPT-5.4 leads
Dolly 2.0-12b: 17.4 (#291), GPT-5.4: 56.4 (#22)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Non-English | 836 | 1465 |
| LMArena Chinese | 836 | 1520 |
| LMArena French | — | 1493 |
| LMArena German | — | 1472 |
| LMArena Japanese | — | 1484 |
| LMArena Korean | — | 1449 |
| LMArena Russian | — | 1480 |
| LMArena Spanish | — | 1453 |
Instruction Following GPT-5.4 leads
Dolly 2.0-12b: 38.9 (#299), GPT-5.4: 77.3 (#25)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Instruction Following | 814 | 1469 |
Long Context Not comparable
Dolly 2.0-12b: —, GPT-5.4: 50.3 (#8)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| CL-bench | — | 27.9% |
| CL-bench Life | — | 21.7% |
| LMArena Longer Query | — | 1474 |
Writing & Preference GPT-5.4 leads
Dolly 2.0-12b: 15.3 (#306), GPT-5.4: 72.1 (#18)
| Benchmark | Dolly 2.0-12b | GPT-5.4 |
|---|---|---|
| LMArena Text | 851 | 1469 |
| LMArena Creative Writing | 864 | 1439 |
| LMArena Multi-Turn | 740 | 1482 |
| EQ-Bench Creative Writing | — | 1840 |
| EQ-Bench 4 | — | 1272 |
Frequently asked questions
Is Dolly 2.0-12b better than GPT-5.4?
GPT-5.4 is the stronger model overall, scoring 59.5 to 24.9 on the Noometry Index.
Is Dolly 2.0-12b or GPT-5.4 better for coding?
GPT-5.4 scores higher on coding benchmarks: 52.8 versus 23.0 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and GPT-5.4 share?
10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and GPT-5.4 has 68.