Model comparison
GLM-5 vs Qwen3.6-35B-A3B
Head-to-head evidence from 33 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GLM-5 #15; Qwen3.6-35B-A3B #31
BenchAlign evidence: GLM-5 supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and Qwen3.6-35B-A3B share 33 comparable benchmark results. 4 of 8 categories are comparable. 17 results are unique to GLM-5; 25 to Qwen3.6-35B-A3B.
Updated July 15, 2026- Shared results
- 33
- GLM-5 only
- 17
- Qwen3.6-35B-A3B only
- 25
- Comparable categories
- 4 / 8
Pick GLM-5 if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if mathematics is the priority or you need the larger 262K context window.
Confidence note. This is a partial-evidence comparison with 33 shared benchmark results across 6 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.
Why this result
GLM-5 is clearly ahead on the provisional aggregate, 63 to 59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GLM-5's sharpest advantage is in knowledge, where it averages 66.6 against 51.8. The single biggest benchmark swing on the page is HLE, 50.4% to 21.4%. Qwen3.6-35B-A3B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B is the reasoning model in the pair, while GLM-5 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. Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 200K for GLM-5.
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-5 | Δ | Qwen3.6-35B-A3B |
|---|---|---|---|
| Math | GLM-556.3 | Margin→ 31.9 | Qwen3.6-35B-A3B88.2 |
| Knowledge | GLM-566.6 | Margin← 14.8 | Qwen3.6-35B-A3B51.8 |
| Coding | GLM-566.3 | Margin→ 7.5 | Qwen3.6-35B-A3B73.8 |
| Agentic | GLM-556.2 | Margin← 4.7 | Qwen3.6-35B-A3B51.5 |
| Reasoning | GLM-560.8 | MarginNo overlap | Qwen3.6-35B-A3BNot measured |
| Multilingual | GLM-583.1 | MarginNo overlap | Qwen3.6-35B-A3BNot measured |
| Multimodal | GLM-5Not measured | MarginNo overlap | Qwen3.6-35B-A3B76.3 |
| Inst. Following | GLM-592.6 | MarginNo overlap | Qwen3.6-35B-A3BNot measured |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HLE
KnowledgeA 50.4%B 21.4%Winner: GLM-5Δ 29HLE: GLM-5 scored 50.4%; Qwen3.6-35B-A3B scored 21.4%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 55.1%B 49.5%Winner: GLM-5Δ 5.6SWE-bench Pro: GLM-5 scored 55.1%; Qwen3.6-35B-A3B scored 49.5%. GLM-5 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 51.5%Winner: GLM-5Δ 4.7Terminal-Bench 2.0: GLM-5 scored 56.2%; Qwen3.6-35B-A3B scored 51.5%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 77.8%B 73.4%Winner: GLM-5Δ 4.4SWE-bench Verified: GLM-5 scored 77.8%; Qwen3.6-35B-A3B scored 73.4%. GLM-5 wins this benchmark. - Source ↗
AIME26
MathA 95.8%B 92.7%Winner: GLM-5Δ 3.1AIME26: GLM-5 scored 95.8%; Qwen3.6-35B-A3B scored 92.7%. GLM-5 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | Qwen3.6-35B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | Qwen3.6-35B-A3BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GLM-574 tok/s | Qwen3.6-35B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-51.64 s | Qwen3.6-35B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5200K | Qwen3.6-35B-A3B262K | Qwen3.6-35B-A3B lists the larger context window. |
Benchmark Deep Dive
AgenticGLM-5 wins18 benchmarks
| Benchmark | GLM-5 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 51.5% | GLM-5 leads |
| Claw-EvalSource | 57.7% | 68.7% | Qwen3.6-35B-A3B leads |
| QwenClawBenchSource | 54.1% | 52.6% | GLM-5 leads |
| τ³-bench resultsSource | 65.6% | 67.2% | Qwen3.6-35B-A3B leads |
| DeepPlanningSource | 14.6% | 25.9% | Qwen3.6-35B-A3B leads |
| ToolathlonSource | 38% | 26.9% | GLM-5 leads |
| MCP AtlasSource | 31.1% | 62.8% | Qwen3.6-35B-A3B leads |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | 60.1% | GLM-5 leads |
| τ²-bench resultsSource | 98.2% | 95.3% | GLM-5 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | — | Not comparable |
| Gert LabsSource | 50.99% | 42.65% | GLM-5 leads |
| QwenWebBenchSource | — | 1397 | Not comparable |
| VITA-BenchSource | — | 35.6% | Not comparable |
| AA Agentic IndexSource | — | 21.4% | Not comparable |
| GDPval-AASource | — | 27.4% | Not comparable |
| GDPval-AASource | — | 1049 | Not comparable |
CodingQwen3.6-35B-A3B wins12 benchmarks
| Benchmark | GLM-5 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | 73.4% | GLM-5 leads |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | 49.5% | GLM-5 leads |
| SWE MultilingualSource | 73.3% | 67.2% | GLM-5 leads |
| SWE-RebenchSource | 62.8% | — | Not comparable |
| React Native EvalsSource | 74.8% | — | Not comparable |
| Terminal-Bench HardSource | 43.2% | 34.8% | GLM-5 leads |
| AA-SciCodeSource | 46.2% | 35.8% | GLM-5 leads |
| Terminal-Bench 2.0Source | — | 51.5% | Not comparable |
| LiveCodeBenchSource | — | 80.4% | Not comparable |
| NL2RepoSource | — | 29.4% | Not comparable |
| AA Coding IndexSource | — | 41.9% | Not comparable |
Reasoning4 benchmarks
KnowledgeGLM-5 wins13 benchmarks
| Benchmark | GLM-5 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| GPQASource | 86% | 86% | Tie |
| GPQA-DSource | 86.0% | — | Not comparable |
| SuperGPQASource | 66.8% | 64.7% | GLM-5 leads |
| MMLU-ProSource | 85.7% | 85.2% | GLM-5 leads |
| MMLU-Pro (Arcee)Source | 85.8% | — | Not comparable |
| HLESource | 50.4% | 21.4% | GLM-5 leads |
| Artificial Analysis Intelligence IndexSource | 39.5% | 31.6% | GLM-5 leads |
| AA-GPQA DiamondSource | 82.0% | 84.1% | Qwen3.6-35B-A3B leads |
| AA-HLESource | 27.2% | 20.2% | GLM-5 leads |
| AA-Omniscience IndexSource | 2.0% | -21.4% | GLM-5 leads |
| AA-Omniscience AccuracySource | 26.9% | 18.9% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 49.7% | GLM-5 leads |
| C-EvalSource | — | 90% | Not comparable |
MathQwen3.6-35B-A3B wins8 benchmarks
| Benchmark | GLM-5 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AIME26Source | 95.8% | 92.7% | GLM-5 leads |
| AIME25 (Arcee)Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 97.5% | 90.7% | GLM-5 leads |
| HMMT Nov 2025Source | 96.9% | 89.1% | GLM-5 leads |
| HMMT Feb 2026Source | 86.4% | 83.6% | GLM-5 leads |
| MMAnswerBenchSource | 82.5% | 78.9% | GLM-5 leads |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.100% | — | Not comparable |
Multilingual2 benchmarks
Multimodal16 benchmarks
| Benchmark | GLM-5 | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Design Arena WebsiteSource | 1282 | — | Not comparable |
| MMMUSource | — | 81.7% | Not comparable |
| MMMU-ProSource | — | 75.3% | Not comparable |
| RealWorldQASource | — | 85.3% | Not comparable |
| OmniDocBench 1.5Source | — | 89.9% | Not comparable |
| CharXivSource | — | 78% | Not comparable |
| SimpleVQASource | — | 58.9% | Not comparable |
| CC-OCRSource | — | 81.9% | Not comparable |
| AI2D_TESTSource | — | 92.7% | Not comparable |
| RefCOCO (avg)Source | — | 92.0% | Not comparable |
| ODINW13Source | — | 50.8% | Not comparable |
| Video-MME (with subtitle)Source | — | 86.6% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 82.5% | Not comparable |
| VideoMMMUSource | — | 83.7% | Not comparable |
| MLVU (M-Avg)Source | — | 86.2% | Not comparable |
| AA-MMMU-ProSource | — | 75.0% | Not comparable |
Frequently Asked Questions (5)
Which is better, GLM-5 or Qwen3.6-35B-A3B?
GLM-5 is ahead on BenchLM's provisional leaderboard, 63 to 59. The biggest single separator in this matchup is HLE, where the scores are 50.4% and 21.4%.
Which is better for knowledge tasks, GLM-5 or Qwen3.6-35B-A3B?
GLM-5 has the edge for knowledge tasks in this comparison, averaging 66.6 versus 51.8. Inside this category, HLE is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5 or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 66.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for math, GLM-5 or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for math in this comparison, averaging 88.2 versus 56.3. Inside this category, HMMT Nov 2025 is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or Qwen3.6-35B-A3B?
GLM-5 has the edge for agentic tasks in this comparison, averaging 56.2 versus 51.5. Inside this category, MCP Atlas is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.