Model comparison
GLM-5.2 vs GPT-4.1 mini
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.6 on the Noometry Index. GPT-4.1 mini costs 3.1× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 33 shared benchmarks.
Summary
- They share 33 benchmarks with published results for both. GLM-5.2 scores higher in 8 categories and GPT-4.1 mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.7 to 24.1.
- The biggest single-benchmark swing is ARC-AGI-1: 77% for GLM-5.2 and 3.5% for GPT-4.1 mini.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-4.1 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 51.1 | 33.6 |
| Released | 2026-06-13 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 131K | 33K |
| Input $ / M tokens | $1.40 | $0.40 |
| Output $ / M tokens | $4.40 | $1.60 |
| Results tracked | 51 | 47 |
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), GPT-4.1 mini: 30.6 (#293)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| SciCode | 50.5% | 40.4% |
| WeirdML | 70.1% | 37.6% |
| LMArena Coding | 1485 | 1367 |
| SWE-bench Verified | 78.7% | — |
| DeepSWE | 43.8% | — |
| FrontierCode | 24.5% | — |
| SWE-bench Verified (bash only) | — | 23.9% |
| Aider Polyglot | — | 32.4% |
| LMArena WebDev | 1603 | — |
| BigCodeBench Instruct | — | 48.9% |
| CadEval | — | 16% |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Too close to call
GLM-5.2: 32.4 (#63), GPT-4.1 mini: 33.3 (#55)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| APEX-Agents | 45.2% | — |
| Berkeley Function Calling Leaderboard | — | 50.5% |
| 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), GPT-4.1 mini: 10.8 (#340)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| ARC-AGI-2 | 22.8% | 0% |
| Kagi LLM Benchmark | 62.6% | 48.6% |
| ARC-AGI-1 | 77% | 3.5% |
| CritPt | 20.9% | 0% |
| Chess Puzzles | 21% | 7% |
| LMArena Hard Prompts | 1480 | 1349 |
| Mystery Game Puzzles | 19% | 7% |
| DTBench | 93.6% | 68.8% |
| LMCA | 45.8% | 21.1% |
| Epoch Capabilities Index | 151.78 | 135.01 |
| SimpleBench | 58.8% | — |
| NYT Connections (extended) | 74.3% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
Math GLM-5.2 leads
GLM-5.2: 55.7 (#43), GPT-4.1 mini: 24.1 (#270)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 6.7% |
| OTIS Mock AIME 2024-2025 | 86.4% | 44.7% |
| LMArena Math | 1482 | 1343 |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| ProofBench | 35% | — |
| Omni-MATH | — | 49.1% |
| MATH Level 5 | — | 87.3% |
| FrontierMath (Feb 2025 set) | — | 4.5% |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#40), GPT-4.1 mini: 34.7 (#194)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| GPQA Diamond | 91.9% | 65.8% |
| SimpleQA Verified | 34.2% | 12.7% |
| LMArena Expert | 1486 | 1338 |
| MMLU-Pro | — | 78.3% |
| GPQA (HELM) | — | 61.4% |
Multimodal Not comparable
GLM-5.2: —, GPT-4.1 mini: 35.8 (#82)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| LMArena Vision | — | 1181 |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-4.1 mini: 45.7 (#166)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| LMArena Non-English | 1459 | 1318 |
| LMArena Chinese | 1519 | 1329 |
| LMArena French | 1479 | 1358 |
| LMArena German | 1468 | 1351 |
| LMArena Japanese | 1451 | 1290 |
| LMArena Korean | 1445 | 1298 |
| LMArena Russian | 1466 | 1324 |
| LMArena Spanish | 1477 | 1319 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), GPT-4.1 mini: 73.7 (#118)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| LMArena Instruction Following | 1465 | 1333 |
| IFEval | — | 90.4% |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), GPT-4.1 mini: 31.8 (#275)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| LMArena Longer Query | 1479 | 1344 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-4.1 mini: 48.6 (#199)
| Benchmark | GLM-5.2 | GPT-4.1 mini |
|---|---|---|
| LMArena Text | 1470 | 1340 |
| LMArena Creative Writing | 1462 | 1300 |
| EQ-Bench Creative Writing | 1757 | 1147 |
| LMArena Multi-Turn | 1469 | 1354 |
| WildBench | — | 83.8% |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-4.1 mini?
GLM-5.2 is the stronger model overall, scoring 51.1 to 33.6 on the Noometry Index. GPT-4.1 mini costs 3.1× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or GPT-4.1 mini?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or GPT-4.1 mini better for coding?
GLM-5.2 scores higher on coding benchmarks: 51.3 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 1M.
How many benchmarks do GLM-5.2 and GPT-4.1 mini share?
33 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-4.1 mini has 47.