Model comparison
GLM-5.2 vs Phi 3 Small 8k Instruct
GLM-5.2 is the stronger model overall, scoring 51.1 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5.2 leads 70.4 to 31.1.
Side by side
| GLM-5.2 | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 51.1 | 29.3 |
| 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 | 51 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-5.2: 51.3 (#41), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1485 | 1101 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| LMArena WebDev | 1603 | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Not comparable
GLM-5.2: 32.4 (#63), Phi 3 Small 8k Instruct: —
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| APEX-Agents | 45.2% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.3 (#52), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1480 | 1100 |
| 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% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 151.78 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1482 | 1151 |
| 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 | — | 17.6% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1486 | 1067 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1459 | 1058 |
| LMArena Chinese | 1519 | 1061 |
| LMArena French | 1479 | 1135 |
| LMArena German | 1468 | 1080 |
| LMArena Japanese | 1451 | 966 |
| LMArena Korean | 1445 | 894 |
| LMArena Russian | 1466 | 1111 |
| LMArena Spanish | 1477 | 1111 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1465 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1479 | 1088 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | GLM-5.2 | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1470 | 1110 |
| LMArena Creative Writing | 1462 | 1083 |
| LMArena Multi-Turn | 1469 | 1068 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is GLM-5.2 better than Phi 3 Small 8k Instruct?
GLM-5.2 is the stronger model overall, scoring 51.1 to 29.3 on the Noometry Index.
Is GLM-5.2 or Phi 3 Small 8k Instruct better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 27.9 in the Noometry coding category.
How many benchmarks do GLM-5.2 and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and Phi 3 Small 8k Instruct has 32.