Model comparison
Dolly 2.0-12b vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 25.5 on the Noometry Index.
Last verified . 9 shared benchmarks.
DatabricksSummary
- They share 9 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and GLM-4.6 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 15.2.
Side by side
| Dolly 2.0-12b | GLM-4.6 | |
|---|---|---|
| Provider | Databricks | Z.ai (Zhipu) |
| Noometry Index | 25.5 | 41.4 |
| Released | 2023-04-11 | 2025-09-30 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 17 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
Dolly 2.0-12b: 23.4 (#332), GLM-4.6: 40.1 (#148)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Coding | 776 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
Dolly 2.0-12b: —, GLM-4.6: 32.3 (#66)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.6 leads
Dolly 2.0-12b: 15.3 (#316), GLM-4.6: 23.7 (#172)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 804 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
| Epoch Capabilities Index | 89.67 | — |
| HellaSwag | 70.8% | — |
| PIQA | 75.4% | — |
| WinoGrande | 61.8% | — |
Math GLM-4.6 leads
Dolly 2.0-12b: 27.3 (#251), GLM-4.6: 39.1 (#111)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Math | 871 | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Not comparable
Dolly 2.0-12b: —, GLM-4.6: 40.2 (#124)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | — | 9.5% |
| LMArena Expert | — | 1431 |
| ARC (AI2) Challenge | 39.6% | — |
| BoolQ | 56.3% | — |
| MMLU | 26.2% | — |
| OpenBookQA | 39.2% | — |
Multilingual GLM-4.6 leads
Dolly 2.0-12b: 17.4 (#296), GLM-4.6: 53.5 (#66)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 836 | 1426 |
| LMArena Chinese | 836 | 1499 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
| LMArena Russian | — | 1419 |
| LMArena Spanish | — | 1436 |
Instruction Following GLM-4.6 leads
Dolly 2.0-12b: 38.7 (#304), GLM-4.6: 74.3 (#98)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 814 | 1410 |
Long Context Not comparable
Dolly 2.0-12b: —, GLM-4.6: 43.4 (#94)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | — | 1422 |
Writing & Preference GLM-4.6 leads
Dolly 2.0-12b: 15.2 (#311), GLM-4.6: 61.1 (#90)
| Benchmark | Dolly 2.0-12b | GLM-4.6 |
|---|---|---|
| LMArena Text | 851 | 1440 |
| LMArena Creative Writing | 864 | 1411 |
| LMArena Multi-Turn | 740 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is Dolly 2.0-12b better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 25.5 on the Noometry Index.
Is Dolly 2.0-12b or GLM-4.6 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 23.4 in the Noometry coding category.
How many benchmarks do Dolly 2.0-12b and GLM-4.6 share?
9 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and GLM-4.6 has 29.