Model comparison
GLM-4.6 vs Olmo 3.1 32b Think
GLM-4.6 is the stronger model overall, scoring 40.9 to 37.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 15 benchmarks with published results for both. GLM-4.6 scores higher in 7 categories and Olmo 3.1 32b Think in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.6 leads 53.6 to 38.3.
Side by side
| GLM-4.6 | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Allen Institute for AI (Ai2) |
| Noometry Index | 40.9 | 37.3 |
| Released | 2025-09-30 | — |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
GLM-4.6: 39.9 (#137), Olmo 3.1 32b Think: 37.1 (#186)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1449 | 1292 |
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1339 | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use Not comparable
GLM-4.6: 32.1 (#60), Olmo 3.1 32b Think: —
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning Olmo 3.1 32b Think leads
GLM-4.6: 23.1 (#168), Olmo 3.1 32b Think: 24.1 (#151)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1272 |
| Kagi LLM Benchmark | 47.4% | — |
| CritPt | 1.1% | — |
Math GLM-4.6 leads
GLM-4.6: 36.4 (#115), Olmo 3.1 32b Think: 33.6 (#170)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1431 | 1305 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 39.6 (#118), Olmo 3.1 32b Think: 35.0 (#178)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1432 | 1294 |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual GLM-4.6 leads
GLM-4.6: 53.6 (#62), Olmo 3.1 32b Think: 38.3 (#226)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1426 | 1210 |
| LMArena Chinese | 1500 | 1241 |
| LMArena French | 1459 | 1262 |
| LMArena German | 1447 | 1260 |
| LMArena Russian | 1418 | 1193 |
| LMArena Spanish | 1436 | 1288 |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1401 | — |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.5 (#93), Olmo 3.1 32b Think: 65.8 (#213)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1410 | 1246 |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#91), Olmo 3.1 32b Think: 38.6 (#190)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1423 | 1272 |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.3 (#86), Olmo 3.1 32b Think: 46.4 (#215)
| Benchmark | GLM-4.6 | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1440 | 1271 |
| LMArena Creative Writing | 1411 | 1226 |
| LMArena Multi-Turn | 1427 | 1252 |
| EQ-Bench Creative Writing | 1411 | — |
Frequently asked questions
Is GLM-4.6 better than Olmo 3.1 32b Think?
GLM-4.6 is the stronger model overall, scoring 40.9 to 37.3 on the Noometry Index.
Is GLM-4.6 or Olmo 3.1 32b Think better for coding?
GLM-4.6 scores higher on coding benchmarks: 39.9 versus 37.1 in the Noometry coding category.
How many benchmarks do GLM-4.6 and Olmo 3.1 32b Think share?
15 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Olmo 3.1 32b Think has 15.