Model comparison
GLM-5.2 vs Phi 3 Mini 4k Instruct
GLM-5.2 is the stronger model overall, scoring 50.9 to 27.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
MicrosoftSummary
- They share 18 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.7 to 27.7.
- The biggest single-benchmark swing is Chess Puzzles: 21% for GLM-5.2 and 0% for Phi 3 Mini 4k Instruct.
Side by side
| GLM-5.2 | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 50.9 | 27.4 |
| Released | 2026-06-13 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $4.40 | — |
| Results tracked | 50 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 50.9 (#37), Phi 3 Mini 4k Instruct: 26.1 (#319)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1484 | 1093 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1604 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 1,047 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Agentic & Tool Use Not comparable
GLM-5.2: 31.6 (#63), Phi 3 Mini 4k Instruct: —
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 21% | 0% |
| LMArena Hard Prompts | 1480 | 1072 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| NYT Connections (extended) | 74.3% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 26.8% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LiveBench Data Analysis | — | 34.7% |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 151.76 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1482 | 1111 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
| LiveBench Math | — | 15.7% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1484 | 1045 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1459 | 1021 |
| LMArena Chinese | 1518 | 1021 |
| LMArena French | 1476 | 1075 |
| LMArena German | 1470 | 1044 |
| LMArena Japanese | 1451 | 935 |
| LMArena Korean | 1445 | 905 |
| LMArena Russian | 1467 | 1022 |
| LMArena Spanish | 1477 | 1084 |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1465 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1479 | 1044 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | GLM-5.2 | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1470 | 1073 |
| LMArena Creative Writing | 1465 | 1037 |
| LMArena Multi-Turn | 1468 | 1018 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is GLM-5.2 better than Phi 3 Mini 4k Instruct?
GLM-5.2 is the stronger model overall, scoring 50.9 to 27.4 on the Noometry Index.
Is GLM-5.2 or Phi 3 Mini 4k Instruct better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 26.1 in the Noometry coding category.
How many benchmarks do GLM-5.2 and Phi 3 Mini 4k Instruct share?
18 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.