Model comparison
Claude Opus 4 vs GLM-4.6
Claude Opus 4 is the stronger model overall, scoring 42.9 to 40.9 on the Noometry Index. GLM-4.6 costs 30× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and GLM-4.6 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 4 leads 47.8 to 39.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 74.3% for Claude Opus 4 and 47.4% for GLM-4.6.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $15 / $75 for Claude Opus 4.
- GLM-4.6 accepts more context: 205K tokens versus 200K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 4 | GLM-4.6 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 42.9 | 40.9 |
| Released | 2025-05-22 | 2025-09-30 |
| Weights | Proprietary | Open |
| Context window | 200K | 205K |
| Max output | 32K | 131K |
| Input $ / M tokens | $15 | $0.60 |
| Output $ / M tokens | $75 | $2.20 |
| Results tracked | 56 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.8 (#55), GLM-4.6: 39.9 (#137)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| SWE-bench Verified (bash only) | 67.6% | 55.4% |
| LMArena Coding | 1442 | 1449 |
| SWE-bench Verified | 70.7% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1339 |
| SciCode | — | 38.4% |
| GSO | 6.9% | — |
| WeirdML | 43.7% | — |
| ALE-Bench | — | 340.82 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.5 (#39), GLM-4.6: 32.1 (#60)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.4 (#104), GLM-4.6: 23.1 (#168)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 47.4% |
| CritPt | 0.3% | 1.1% |
| LMArena Hard Prompts | 1399 | 1440 |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 35.7% | — |
| EnigmaEval | 5.6% | — |
| DTBench | 81.6% | — |
| LMCA | 37.4% | — |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 40.2 (#80), GLM-4.6: 36.4 (#115)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Math | 1391 | 1431 |
| FrontierMath (Feb 2025 set) | 4.5% | 3.8% |
| FrontierMath Tier 4 (v1) | 4.2% | 2.1% |
| OTIS Mock AIME 2024-2025 | 64.4% | — |
| Omni-MATH | 61.6% | — |
| MATH Level 5 | 85% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 43.9 (#82), GLM-4.6: 39.6 (#118)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 12% | 9.5% |
| LMArena Expert | 1384 | 1432 |
| GPQA Diamond | 76.3% | — |
| Humanity's Last Exam | 10.7% | — |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Not comparable
Claude Opus 4: 30.9 (#101), GLM-4.6: —
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1192 | — |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual GLM-4.6 leads
Claude Opus 4: 49.0 (#133), GLM-4.6: 53.6 (#62)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1362 | 1426 |
| LMArena Chinese | 1386 | 1500 |
| LMArena French | 1370 | 1459 |
| LMArena German | 1391 | 1447 |
| LMArena Japanese | 1332 | 1394 |
| LMArena Korean | 1318 | 1401 |
| LMArena Russian | 1392 | 1418 |
| LMArena Spanish | 1388 | 1436 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.3 (#26), GLM-4.6: 74.5 (#93)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1410 |
| IFEval | 91.8% | — |
Long Context GLM-4.6 leads
Claude Opus 4: 39.5 (#167), GLM-4.6: 43.4 (#91)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1422 | 1423 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Too close to call
Claude Opus 4: 61.4 (#85), GLM-4.6: 61.3 (#86)
| Benchmark | Claude Opus 4 | GLM-4.6 |
|---|---|---|
| LMArena Text | 1377 | 1440 |
| LMArena Creative Writing | 1386 | 1411 |
| EQ-Bench Creative Writing | 1580 | 1411 |
| LMArena Multi-Turn | 1396 | 1427 |
| Short-Story Creative Writing | 83.6% | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than GLM-4.6?
Claude Opus 4 is the stronger model overall, scoring 42.9 to 40.9 on the Noometry Index. GLM-4.6 costs 30× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 4 or GLM-4.6?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; Claude Opus 4 lists at $15 and $75.
Is Claude Opus 4 or GLM-4.6 better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.8 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 200K.
How many benchmarks do Claude Opus 4 and GLM-4.6 share?
24 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and GLM-4.6 has 29.