Model comparison
GLM-5.3 vs Phi-2
GLM-5.3 has enough public results to be ranked (#26); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
MicrosoftSummary
- They share 1 benchmark with published results for both.
Side by side
| GLM-5.3 | Phi-2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 54.8 | — |
| Released | 2026-08-14 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 42 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GLM-5.3: 59.5 (#14), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| DeepSWE | 69% | — |
| FrontierCode | 40.1% | — |
| CursorBench | 42.6% | — |
| LMArena WebDev | 1622 | — |
| FrontierSWE | 30.2% | — |
| SciCode | 59% | — |
| WeirdML | 75.4% | — |
| LMArena Coding | 1496 | — |
| ALE-Bench | 1,317 | — |
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
GLM-5.3: 36.4 (#38), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| APEX-Agents | 56.6% | — |
| Vending-Bench 2 | 8,164 | — |
Reasoning Not comparable
GLM-5.3: 46.1 (#46), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 155.61 | 107.94 |
| NYT Connections (extended) | 74.2% | — |
| CritPt | 19.1% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | 1489 | — |
| Mystery Game Puzzles | 33% | — |
| DTBench | 87.7% | — |
| LMCA | 55.5% | — |
| Adversarial NLI | — | 42.5% |
| Bench to the Future 3 | 0.15 | — |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
GLM-5.3: 62.3 (#33), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 68.8% | — |
| FrontierMath Tier 4 | 29.3% | — |
| OTIS Mock AIME 2024-2025 | 91.1% | — |
| ProofBench | 49% | — |
| LMArena Math | 1489 | — |
Knowledge Not comparable
GLM-5.3: 58.3 (#37), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| SimpleQA Verified | 41% | — |
| LMArena Expert | 1516 | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Multilingual Not comparable
GLM-5.3: 55.7 (#28), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| LMArena Non-English | 1457 | — |
| LMArena Chinese | 1528 | — |
| LMArena French | 1499 | — |
| LMArena German | 1499 | — |
| LMArena Japanese | 1453 | — |
| LMArena Korean | 1472 | — |
| LMArena Russian | 1463 | — |
| LMArena Spanish | 1460 | — |
Instruction Following Not comparable
GLM-5.3: 77.5 (#23), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| LMArena Instruction Following | 1477 | — |
Long Context Not comparable
GLM-5.3: 45.4 (#41), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1482 | — |
Writing & Preference Not comparable
GLM-5.3: 75.7 (#6), Phi-2: —
| Benchmark | GLM-5.3 | Phi-2 |
|---|---|---|
| LMArena Text | 1471 | — |
| LMArena Creative Writing | 1457 | — |
| EQ-Bench Creative Writing | 2075 | — |
| LMArena Multi-Turn | 1472 | — |
Frequently asked questions
Is GLM-5.3 better than Phi-2?
GLM-5.3 has enough public results to be ranked (#26); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do GLM-5.3 and Phi-2 share?
1 benchmark has published results for both models. GLM-5.3 has 42 scored results on Noometry and Phi-2 has 11.