GLM-4.6V
- Input
- $0.30/M tok
- Output
- $0.90/M tok
- Blended
- $0.45/M tok · 3:1
- Speed
- 85tok/s
- Context
- 128Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: GLM-4.6V (Non-reasoning). Price = AA median host price.
Rankings
Writing & chat
Verified#107 / 162rank by quality28.3±5.1quality / 1003/5 benchmarks measuredVision
Verified#89 / 98rank by quality19.1±8.2quality / 1001/6 benchmarks measuredHard reasoning
Verified#169 / 218rank by quality20.9±5.9quality / 1002/4 benchmarks measuredAgents
Verified#128 / 187rank by quality20.0±10.0quality / 1001/7 benchmarks measured
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.
- Hardware
- 2× H200 141GB
- FP8 weights
- Throughput
- ~7,235 tok/s
- many requests batched
- Price
- $0.12–0.97 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~72 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (106B params, 12B active per token) + 25% KV-cache headroom ≈ 133 GB
- 2× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~7,235 output tok/s aggregate at batch 260 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~77,923 tok/s
- Low = 75% utilization at the low GPU price; high = 20% at the high price
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Writing & chat
IFBenchVerified
#122 of 13927.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #121Kimi Linear 48B A3B Instruct28.1%
- #122GLM-4.6V27.9%
- #123NVIDIA Nemotron Nano 9B V227.1%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~last of 5 (estimated)below measured range (<81.3%)
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Few votesVerified
#44 of 561361 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #43Qwen3 Next 80B A3B Instruct1386
- #44GLM-4.6VFew votes1361
- #45Trinity Large Thinking1350
lmarena.ai · 2026-09-13
LMArena Text (Elo)Few votesVerified
#44 of 561378 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #43Qwen3 Next 80B A3B Instruct1399
- #44GLM-4.6VFew votes1378
- #45Trinity Large Thinking1369
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1361 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24GLM-4.6VEstimated1361
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Vision
CharXiv ReasoningEstimated
~last of 12 (estimated)below measured range (<74.5%)
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~last of 8 (estimated)below measured range (<75.8%)
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#46 of 48 (estimated)~0.1%
- #1Muse Wonder Full32.6%
- #2GPT-6 Astra31.0%
- #45Ministral 3 8B0.8%
- ~#46GLM-4.6VEstimated0.1%
- #46Ministral 3 3B0.0%
No published score — estimated from related benchmarks
ChartographyEstimated
~last of 25 (estimated)below measured range (<9.0%)
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#143 of 19256.6%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #141NVIDIA Nemotron Nano 12B v2 VL57.2%
- #143GLM-4.6V56.6%
- #144Granite 4.2 3B55.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~43.6%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23GLM-4.6VEstimated43.6%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#96 of 103 (estimated)~6.7
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #95Devstral Small 27.5
- ~#96GLM-4.6VEstimated6.7
- #96Llama 4 Scout6.5
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#60 of 11930.7%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #59Gemma 4 12B31.9%
- #60GLM-4.6V30.7%
- #61NVIDIA Nemotron 3 Nano 4B28.1%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~53.5%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12GLM-4.6VEstimated53.5%
- #12Nemotron 3.5 Super VL NVFP452.3%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~#3 of 5 (estimated)~53.8%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#21 of 22 (estimated)~42.1%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21GLM-4.6VEstimated42.1%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~713 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60GLM-4.6VEstimated713
- #60MiniCPM5-2B694
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.4%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79GLM-4.6VEstimated0.4%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#80 of 91 (estimated)~5.6%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #78HyperNova 60B 26055.6%
- ~#80GLM-4.6VEstimated5.6%
- #80Qwen3 Coder Next5.4%
No published score — estimated from related benchmarks