Compare / Qwen3.5-397B-A17B vs GLM-5
Qwen3.5-397B-A17B vs GLM-5
Which is cheaper, which is more capable, and which does better at each kind of work, from 25 results on 4 sources that measured both models.
Of the 25 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5). See also Alibaba vs Z.ai, every model from both labs.
Qwen3.5-397B-A17B or GLM-5? The short answer
Pick GLM-5: it scores higher (Intelligence Index 27.9 against 21.4) at about the same price.
- They cost about the same: $1.29 and $1.35 per million tokens (three input to one output).
- GLM-5 scores higher on the Artificial Analysis Intelligence Index: 27.9 against 21.4.
- Qwen3.5-397B-A17B is newer: released 13 Feb 2026, against 12 Feb 2026 for GLM-5.
- On third-party benchmarks, on the results both models have: Qwen3.5-397B-A17B does better for agents and tool use; GLM-5 for reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3.5-397B-A17B | GLM-5 | |
|---|---|---|
| Price per million tokens | $0.55 in · $3.50 out | $0.95 in · $2.55 out |
| Blended (3 in : 1 out) | $1.29 | $1.35 |
| Cheapest host, blended | $0.88 (Alibaba) | $0.93 (GMICloud, FP8) |
| Intelligence Index | 21.4 | 27.9 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 90 | – |
| Context window | 262,144 tokens | 204,800 tokens |
| Released | 13 Feb 2026 (newer) | 12 Feb 2026 |
| Weights | Open | Open |
| Developer based in | China | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Qwen3.5-397B-A17B | GLM-5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 80 · 54 of 387 measured | 1,442 | 1,458 |
| Overall · Text factualityArena rating, higher is better 70 · 56 of 163 measured | 1,445 | 1,452 |
| Business, management and finance · TextArena rating, higher is better 73 · 65 of 380 measured | 1,446 | 1,451 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 97 · 60 of 243 measured | 21.4no reasoning | 27.9 |
| GPQA Diamond% of questions, higher is better 53 · 101 of 231 measured | 89.3% | 82.0% |
| Humanity's Last Exam% of questions, higher is better 77 · 75 of 242 measured | 29.0% | 29.3% |
| τ²-bench reported by τ²-bench · 3 results | ||
| Task success (pass^1) · tau2 v1.0.1, airline% of tasks, higher is better 5 · 3 of 7 measured | 81.5%thinking reasoning, tau2 | 82.5%thinking reasoning, tau2 |
| Task success (pass^1) · tau2 v1.0.1, retail% of tasks, higher is better 1 · 6 of 7 measured | 84.4%thinking reasoning, tau2 | 73.7%thinking reasoning, tau2 |
| Task success (pass^1) · tau2 v1.0.1, telecom% of tasks, higher is better 1 · 6 of 7 measured | 97.8%thinking reasoning, tau2 | 86.8%thinking reasoning, tau2 |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 77 · 59 of 230 measured | 50.1no reasoning | 55.0thinking reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 134 · 177 of 230 measured | 23.0%no reasoning | 34.0%thinking reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 164 · 11 of 230 measured | 0.33no reasoning | 0.40no reasoning |
Show all 25 results (13 more)
| Measure | Qwen3.5-397B-A17B | GLM-5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better 86 · 33 of 385 measured | 1,405 | 1,449 |
| Expert prompts · TextArena rating, higher is better 67 · 61 of 338 measured | 1,477 | 1,482 |
| Instruction following · TextArena rating, higher is better 78 · 60 of 387 measured | 1,434 | 1,446 |
| Writing, literature and language · TextArena rating, higher is better 80 · 46 of 386 measured | 1,421 | 1,449 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 8 · 41 of 195 measured | 78.8% | 72.3% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 66 · 76 of 233 measured | 77.3% | 75.7% |
| Terminal-Bench Hard% of tasks, higher is better 34 · 26 of 190 measured | 40.9% | 43.2% |
| τ²-bench telecom% of tasks, higher is better 16 · 6 of 193 measured | 95.6% | 98.2% |
| τ²-bench reported by τ²-bench · 5 results | ||
| Consistency (pass^4) · tau2 v1.0.1, airline% of tasks, higher is better 4 · 2 of 7 measured | 68.0%thinking reasoning, tau2 | 70.0%thinking reasoning, tau2 |
| Consistency (pass^4) · tau2 v1.0.1, banking knowledge, text-emb-3-large retrieval% of tasks, higher is better | 5.2%thinking reasoning, tau2 | 3.1%thinking reasoning, tau2 |
| Consistency (pass^4) · tau2 v1.0.1, retail% of tasks, higher is better 1 · 6 of 7 measured | 59.7%thinking reasoning, tau2 | 43.9%thinking reasoning, tau2 |
| Consistency (pass^4) · tau2 v1.0.1, telecom% of tasks, higher is better 1 · 7 of 7 measured | 92.1%thinking reasoning, tau2 | 62.3%thinking reasoning, tau2 |
| Task success (pass^1) · tau2 v1.0.1, banking knowledge, text-emb-3-large retrieval% of tasks, higher is better | 9.8%thinking reasoning, tau2 | 9.8%thinking reasoning, tau2 |
Compare them with other models
Quick answers
Is Qwen3.5-397B-A17B better than GLM-5?
Pick GLM-5: it scores higher (Intelligence Index 27.9 against 21.4) at about the same price.
Which is cheaper, Qwen3.5-397B-A17B or GLM-5?
They cost about the same: $1.29 and $1.35 per million tokens (three input to one output).
Which is better for agents and tool use, Qwen3.5-397B-A17B or GLM-5?
Qwen3.5-397B-A17B ranks 70 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 100 for GLM-5.
Which is better for reasoning and knowledge, Qwen3.5-397B-A17B or GLM-5?
Qwen3.5-397B-A17B ranks 73 of 198 models on sale for hard questions across science, maths and general knowledge, against 75 for GLM-5.
Which is better for writing, Qwen3.5-397B-A17B or GLM-5?
GLM-5 ranks 52 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 69 for Qwen3.5-397B-A17B.
Which is better for sticking to the facts, Qwen3.5-397B-A17B or GLM-5?
GLM-5 ranks 69 of 152 models on sale for summarising without inventing things, and factual answers, against 75 for Qwen3.5-397B-A17B.
Which has the bigger context window, Qwen3.5-397B-A17B or GLM-5?
Qwen3.5-397B-A17B: 262,144 tokens, against 204,800 for GLM-5.
Run Qwen3.5-397B-A17B and GLM-5 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.