Model comparison
GLM-4.6 vs Qwen3.5 397B
Head-to-head evidence from 11 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GLM-4.6 #85 (Supported); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-4.6 and Qwen3.5 397B share 11 comparable benchmark results. 1 of 8 categories are comparable. 3 results are unique to GLM-4.6; 44 to Qwen3.5 397B.
Updated July 23, 2026- Shared results
- 11
- GLM-4.6 only
- 3
- Qwen3.5 397B only
- 44
- Comparable categories
- 1 / 8
Pick Qwen3.5 397B if you want the stronger benchmark profile. GLM-4.6 only becomes the better choice if you need the larger 200K context window or you want the stronger reasoning-first profile.
Confidence note. This is a partial-evidence comparison with 11 shared benchmark results across 5 evidence categories; 1 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
Qwen3.5 397B has the cleaner BenchAlign overall profile here, landing at 57.01 versus 55.12. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.5 397B's sharpest advantage is in mathematics, where it averages 90.6 against 3.4.
GLM-4.6 is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GLM-4.6 gives you the larger context window at 200K, compared with 128K for Qwen3.5 397B.
Category breakdown
Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.
| Category | GLM-4.6 | Δ | Qwen3.5 397B |
|---|---|---|---|
| Math | GLM-4.63.4 | Margin→ 87.2 | Qwen3.5 397B90.6 |
| Agentic | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B56.5 |
| Coding | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B66.5 |
| Reasoning | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B63.2 |
| Knowledge | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B56.6 |
| Multilingual | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B84.7 |
| Multimodal | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B79.6 |
| Inst. Following | GLM-4.6Not measured | MarginNo overlap | Qwen3.5 397B92.6 |
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-4.6 | Qwen3.5 397B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-4.6Not available | Qwen3.5 397B$0.6 input / $3.6 output | A complete price comparison is not available. |
| Generation speedtokens per second | GLM-4.6Not available | Qwen3.5 397B96 tok/s | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-4.6Not available | Qwen3.5 397B2.44 s | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-4.6200K | Qwen3.5 397B128K | GLM-4.6 lists the larger context window. |
Benchmark Deep Dive
Agentic18 benchmarks
| Benchmark | GLM-4.6 | Qwen3.5 397B | Result |
|---|---|---|---|
| τ²-bench resultsSource | 76.9% | 95.6% | Qwen3.5 397B leads |
| Terminal-Bench 2.0Source | — | 52.5% | Not comparable |
| BrowseCompSource | — | 62% | Not comparable |
| Claw-EvalSource | — | 56.8% | Not comparable |
| QwenClawBenchSource | — | 51.8% | Not comparable |
| τ³-bench resultsSource | — | 68.4% | Not comparable |
| VITA-BenchSource | — | 43.7% | Not comparable |
| DeepPlanningSource | — | 37.6% | Not comparable |
| ToolathlonSource | — | 36.3% | Not comparable |
| MCP AtlasSource | — | 46.1% | Not comparable |
| MCP-TasksSource | — | 74.2% | Not comparable |
| WideResearchSource | — | 74.0% | Not comparable |
| Gert LabsSource | — | 46.76% | Not comparable |
| ResearchClawBenchSource | — | 14.2% | Not comparable |
| AA Agentic IndexSource | — | 19.9% | Not comparable |
| APEX-Agents-AASource | — | 15.3% | Not comparable |
| GDPval-AASource | — | 23.1% | Not comparable |
| GDPval-AASource | — | 962 | Not comparable |
Coding6 benchmarks
Reasoning4 benchmarks
Knowledge12 benchmarks
| Benchmark | GLM-4.6 | Qwen3.5 397B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 23.0% | 33.7% | Qwen3.5 397B leads |
| AA-GPQA DiamondSource | 63.2% | 89.3% | Qwen3.5 397B leads |
| AA-HLESource | 5.2% | 27.3% | Qwen3.5 397B leads |
| AA-Omniscience IndexSource | -31.6% | -29.8% | Qwen3.5 397B leads |
| AA-Omniscience AccuracySource | 20.8% | 31.4% | Qwen3.5 397B leads |
| AA-Omniscience Hallucination RateSource | 66.1% | 89.1% | GLM-4.6 leads |
| GPQASource | — | 88.4% | Not comparable |
| SuperGPQASource | — | 70.4% | Not comparable |
| MMLU-ProSource | — | 87.8% | Not comparable |
| MMLU-ReduxSource | — | 94.9% | Not comparable |
| C-EvalSource | — | 93% | Not comparable |
| HLESource | — | 28.7% | Not comparable |
MathQwen3.5 397B wins7 benchmarks
| Benchmark | GLM-4.6 | Qwen3.5 397B | Result |
|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)Source | 3.819% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.128% | — | Not comparable |
| AIME26Source | — | 93.3% | Not comparable |
| HMMT Feb 2025Source | — | 94.8% | Not comparable |
| HMMT Nov 2025Source | — | 92.7% | Not comparable |
| HMMT Feb 2026Source | — | 87.9% | Not comparable |
| MMAnswerBenchSource | — | 80.9% | Not comparable |
Multilingual2 benchmarks
Multimodal7 benchmarks
Frequently Asked Questions (2)
Which is better, GLM-4.6 or Qwen3.5 397B?
Qwen3.5 397B is ahead on BenchLM's BenchAlign leaderboard, 57.01 to 55.12.
Which is better for math, GLM-4.6 or Qwen3.5 397B?
Qwen3.5 397B has the edge for math in this comparison, averaging 90.6 versus 3.4. GLM-4.6 stays close enough that the answer can still flip depending on your workload.
Related Comparisons
Explore More
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.