Model comparison
GLM-4.6V vs Phi-2
GLM-4.6V has enough public results to be ranked (#133); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
MicrosoftSide by side
| GLM-4.6V | Phi-2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 40.9 | — |
| Released | 2025-12-08 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 12 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-4.6V: 40.2 (#128), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Coding | 1390 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
GLM-4.6V: 26.5 (#117), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Hard Prompts | 1368 | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| Epoch Capabilities Index | — | 107.62 |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Knowledge Not comparable
GLM-4.6V: 37.4 (#148), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Expert | 1372 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multimodal Not comparable
GLM-4.6V: 34.2 (#83), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Vision | 1164 | — |
Multilingual Not comparable
GLM-4.6V: 48.8 (#135), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1426 | — |
| LMArena Russian | 1341 | — |
Instruction Following Not comparable
GLM-4.6V: 71.6 (#145), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1351 | — |
Long Context Not comparable
GLM-4.6V: 41.3 (#138), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1358 | — |
Writing & Preference Not comparable
GLM-4.6V: 56.8 (#132), Phi-2: —
| Benchmark | GLM-4.6V | Phi-2 |
|---|---|---|
| LMArena Text | 1377 | — |
| LMArena Creative Writing | 1347 | — |
| LMArena Multi-Turn | 1359 | — |
Frequently asked questions
Is GLM-4.6V better than Phi-2?
GLM-4.6V has enough public results to be ranked (#133); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do GLM-4.6V and Phi-2 share?
0 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and Phi-2 has 11.