GLM 5V Turbo vs Qwen3.5 397B A17B
Wins 1 of 7 areas
Agents
Wins 5 of 7 areas
Coding · Reasoning · Images and charts · Long documents · Following instructions
Qwen3.5 397B A17B is the stronger all-rounder.GLM 5V Turbo is better at agents.
Scores updated · 19 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking03Qwen3.5 397B A17B3 of 3 tests
- CodingWriting and fixing software02Qwen3.5 397B A17B2 of 3 tests · 1 tie
- Images and chartsUnderstanding pictures, charts and video01Qwen3.5 397B A17B1 of 2 tests · 1 tie
- Long documentsFinding answers in very long texts01Qwen3.5 397B A17B1 of 1 test
- Following instructionsDoing exactly what it is asked01Qwen3.5 397B A17B1 of 1 test
- AgentsCarrying out multi-step tasks on its own10GLM 5V Turbo1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Agents, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
Qwen3.5 397B A17B costs 19% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Qwen3.5 397B A17B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+17.7points ahead
- Very hard expert questions across many subjectsHumanity's Last Exam+11.9points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+8.4points ahead
Where GLM 5V Turbo pulls ahead
- Real work tasks from 44 professionsGDPVal+26.6points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+20.1points ahead
Every test, side by side
All 19 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingQwen3.5 397B A17B
- Terminal-Bench HardQwen3.5 397B A17B by 8.332.640.9+8.3
- SciCodeQwen3.5 397B A17B by 1.343.544.8+1.3
- LMArena · WebDevtie14011400tie
ReasoningQwen3.5 397B A17B
- Humanity's Last ExamQwen3.5 397B A17B by 11.917.129+11.9
- GPQA DiamondQwen3.5 397B A17B by 8.480.989.3+8.4
- CritPtQwen3.5 397B A17B by 1.10.61.7+1.1
FactsEven
- AA-Omniscience · Non-hallucinationGLM 5V Turbo by 20.131.211.1+20.1
- AA-Omniscience · AccuracyQwen3.5 397B A17B by 1.529.330.8+1.5
Images and chartsQwen3.5 397B A17B
- MMMU-ProQwen3.5 397B A17B by 4.572.877.3+4.5
- LMArena · Visiontie12641264tie
Following instructionsQwen3.5 397B A17B
- IFBenchQwen3.5 397B A17B by 17.761.178.8+17.7
Other results6 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA Agentic IndexGLM 5V Turbo by 50.561.110.6+50.5
- Artificial Analysis Coding IndexQwen3.5 397B A17B by 1236.248.2+12
- AA-OmniscienceGLM 5V Turbo by 11.4-19.3-30.8+11.4
- PinchBenchQwen3.5 397B A17B by 5.980.786.6+5.9
- AA IntelligenceGLM 5V Turbo by 5.123.518.4+5.1
- τ²-Bench Telecom (AA run)GLM 5V Turbo by 2.998.595.6+2.9
Questions people ask
Which is better, GLM 5V Turbo or Qwen3.5 397B A17B?
Qwen3.5 397B A17B wins five of the seven areas where both have results: coding, reasoning, images and charts, long documents and following instructions. GLM 5V Turbo wins agents. They are level on facts.
Which is better for coding?
Qwen3.5 397B A17B. It wins 2 of the 3 coding tests both models report; GLM 5V Turbo wins none, and 1 is a tie.
Which is cheaper?
GLM 5V Turbo costs $1.20 per million input tokens and $4.00 per million output tokens; Qwen3.5 397B A17B costs $0.60 and $3.60. That makes Qwen3.5 397B A17B about 19% cheaper for the same work.
How do you compare the two?
We use the 19 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 6 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.