Model comparison
GLM-5 vs Qwen3.5-122B-A10B
Head-to-head evidence from 19 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GLM-5 #28 (Supported); Qwen3.5-122B-A10B #47 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GLM-5 and Qwen3.5-122B-A10B share 19 comparable benchmark results. 6 of 8 categories are comparable. 30 results are unique to GLM-5; 12 to Qwen3.5-122B-A10B.
Updated July 23, 2026- Shared results
- 19
- GLM-5 only
- 30
- Qwen3.5-122B-A10B only
- 12
- Comparable categories
- 6 / 8
Pick GLM-5 if you want the stronger benchmark profile. Qwen3.5-122B-A10B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.
Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 6 evidence categories; 6 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 BenchAlign aggregate, 66.06 to 60.56. 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 multilingual, where it averages 83.1 against 82.2. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 56.2% to 49.4%. Qwen3.5-122B-A10B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
GLM-5 is also the more expensive model on tokens at $1.00 input / $3.20 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for Qwen3.5-122B-A10B. That is roughly Infinityx on output cost alone. Qwen3.5-122B-A10B 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. Qwen3.5-122B-A10B 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 | Qwen3.5-122B-A10B |
|---|---|---|---|
| Knowledge | GLM-566.4 | Margin→ 17.2 | Qwen3.5-122B-A10B83.6 |
| Coding | GLM-566.3 | Margin→ 5.7 | Qwen3.5-122B-A10B72.0 |
| Multilingual | GLM-583.1 | Margin← 0.9 | Qwen3.5-122B-A10B82.2 |
| Inst. Following | GLM-592.6 | Margin→ 0.8 | Qwen3.5-122B-A10B93.4 |
| Reasoning | GLM-560.8 | Margin← 0.6 | Qwen3.5-122B-A10B60.2 |
| Agentic | GLM-556.2 | Margin→ 0.2 | Qwen3.5-122B-A10B56.4 |
| Math | GLM-556.3 | MarginNo overlap | Qwen3.5-122B-A10BNot measured |
| Multimodal | GLM-5Not measured | MarginNo overlap | Qwen3.5-122B-A10B77.2 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 56.2%B 49.4%Winner: GLM-5Δ 6.8Terminal-Bench 2.0: GLM-5 scored 56.2%; Qwen3.5-122B-A10B scored 49.4%. GLM-5 wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 77.8%B 72%Winner: GLM-5Δ 5.8SWE-bench Verified: GLM-5 scored 77.8%; Qwen3.5-122B-A10B scored 72%. GLM-5 wins this benchmark. - Source ↗
MMLU-Pro
KnowledgeA 85.7%B 86.7%Winner: Qwen3.5-122B-A10BΔ 1MMLU-Pro: GLM-5 scored 85.7%; Qwen3.5-122B-A10B scored 86.7%. Qwen3.5-122B-A10B wins this benchmark. - Source ↗
MMLU-ProX
MultilingualA 83.1%B 82.2%Winner: GLM-5Δ 0.9MMLU-ProX: GLM-5 scored 83.1%; Qwen3.5-122B-A10B scored 82.2%. GLM-5 wins this benchmark. - Source ↗
IFEval
Inst. FollowingA 92.6%B 93.4%Winner: Qwen3.5-122B-A10BΔ 0.8IFEval: GLM-5 scored 92.6%; Qwen3.5-122B-A10B scored 93.4%. Qwen3.5-122B-A10B wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GLM-5 | Qwen3.5-122B-A10B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GLM-5$1 input / $3.2 output | Qwen3.5-122B-A10B$0 input / $0 output | Qwen3.5-122B-A10B has the lower combined listed price. |
| Generation speedtokens per second | GLM-574 tok/s | Qwen3.5-122B-A10BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GLM-51.64 s | Qwen3.5-122B-A10BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GLM-5200K | Qwen3.5-122B-A10B262K | Qwen3.5-122B-A10B lists the larger context window. |
Benchmark Deep Dive
AgenticQwen3.5-122B-A10B wins18 benchmarks
| Benchmark | GLM-5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 56.2% | 49.4% | GLM-5 leads |
| Claw-EvalSource | 57.7% | — | Not comparable |
| QwenClawBenchSource | 54.1% | — | Not comparable |
| τ³-bench resultsSource | 65.6% | — | Not comparable |
| DeepPlanningSource | 14.6% | — | Not comparable |
| ToolathlonSource | 38% | — | Not comparable |
| MCP AtlasSource | 31.1% | — | Not comparable |
| MCP-TasksSource | 60.8% | — | Not comparable |
| WideResearchSource | 69.8% | — | Not comparable |
| τ²-bench resultsSource | 98.2% | 93.6% | GLM-5 leads |
| CyberGymSource | 43.2% | — | Not comparable |
| APEX-Agents-AASource | 14.5% | — | Not comparable |
| Gert LabsSource | 50.99% | — | Not comparable |
| BrowseCompSource | — | 63.8% | Not comparable |
| OSWorld-VerifiedSource | — | 58% | Not comparable |
| AA Agentic IndexSource | — | 20.7% | Not comparable |
| GDPval-AASource | — | 23.9% | Not comparable |
| GDPval-AASource | — | 978 | Not comparable |
CodingQwen3.5-122B-A10B wins8 benchmarks
| Benchmark | GLM-5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 77.8% | 72% | GLM-5 leads |
| SWE-bench Verified*Source | 72.8% | — | Not comparable |
| SWE-bench ProSource | 55.1% | — | Not comparable |
| SWE MultilingualSource | 73.3% | — | Not comparable |
| SWE-RebenchSource | 62.8% | — | Not comparable |
| React Native EvalsSource | 74.8% | — | Not comparable |
| AA-SciCodeSource | 46.2% | 42.0% | GLM-5 leads |
| AA Coding IndexSource | — | 45.7% | Not comparable |
ReasoningGLM-5 wins4 benchmarks
KnowledgeQwen3.5-122B-A10B wins12 benchmarks
| Benchmark | GLM-5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| GPQASource | 86% | 86.6% | Qwen3.5-122B-A10B leads |
| GPQA-DSource | 86.0% | — | Not comparable |
| SuperGPQASource | 66.8% | 67.1% | Qwen3.5-122B-A10B leads |
| MMLU-ProSource | 85.7% | 86.7% | Qwen3.5-122B-A10B leads |
| MMLU-Pro (Arcee)Source | 85.8% | — | Not comparable |
| HLESource | 50.4% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 39.5% | 32.3% | GLM-5 leads |
| AA-GPQA DiamondSource | 82.0% | 85.7% | Qwen3.5-122B-A10B leads |
| AA-HLESource | 27.2% | 23.4% | GLM-5 leads |
| AA-Omniscience IndexSource | 2.0% | -39.6% | GLM-5 leads |
| AA-Omniscience AccuracySource | 26.9% | 24.7% | GLM-5 leads |
| AA-Omniscience Hallucination RateSource | 34.0% | 85.5% | GLM-5 leads |
Math8 benchmarks
| Benchmark | GLM-5 | Qwen3.5-122B-A10B | Result |
|---|---|---|---|
| AIME26Source | 95.8% | — | Not comparable |
| AIME25 (Arcee)Source | 93.3% | — | Not comparable |
| HMMT Feb 2025Source | 97.5% | — | Not comparable |
| HMMT Nov 2025Source | 96.9% | — | Not comparable |
| HMMT Feb 2026Source | 86.4% | — | Not comparable |
| MMAnswerBenchSource | 82.5% | — | Not comparable |
| FrontierMath v2 (Tiers 1-3)Source | 16.434% | — | Not comparable |
| FrontierMath v2 (Tier 4)Source | 2.100% | — | Not comparable |
MultilingualGLM-5 wins2 benchmarks
Multimodal7 benchmarks
Frequently Asked Questions (7)
Which is better, GLM-5 or Qwen3.5-122B-A10B?
GLM-5 is ahead on BenchLM's BenchAlign leaderboard, 66.06 to 60.56. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 56.2% and 49.4%.
Which is better for knowledge tasks, GLM-5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for knowledge tasks in this comparison, averaging 83.6 versus 66.4. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, GLM-5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for coding in this comparison, averaging 72 versus 66.3. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.
Which is better for reasoning, GLM-5 or Qwen3.5-122B-A10B?
GLM-5 has the edge for reasoning in this comparison, averaging 60.8 versus 60.2. Inside this category, AA-LCR is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GLM-5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for agentic tasks in this comparison, averaging 56.4 versus 56.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Which is better for instruction following, GLM-5 or Qwen3.5-122B-A10B?
Qwen3.5-122B-A10B has the edge for instruction following in this comparison, averaging 93.4 versus 92.6. Inside this category, AA-IFBench is the benchmark that creates the most daylight between them.
Which is better for multilingual tasks, GLM-5 or Qwen3.5-122B-A10B?
GLM-5 has the edge for multilingual tasks in this comparison, averaging 83.1 versus 82.2. Inside this category, MMLU-ProX is the benchmark that creates the most daylight between them.
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.