INTELLECT-3
- Input
- —
- Output
- —
- Speed
- ~94tok/sest.
- Context
- 131Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: INTELLECT-3 (based on GLM-4.5-Air). Price = AA median host price.
Rankings
Self-hostingEstimated
How we estimate →What it would cost to run these open weights yourself on rented GPUs. No API sells this model, so this is its price on the chart.
- 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
#102 of 13934.0%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #101Sarvam 105B34.4%
- #102INTELLECT-334.0%
- #103Gemma 4 E2B33.6%
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
#47 of 561327 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #46gpt-oss-120b1338
- #47INTELLECT-3Few votes1327
- #48Llama 4 Maverick1311
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#46 of 561356 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #45Trinity Large Thinking1369
- #46INTELLECT-31356
- #47gpt-oss-120b1352
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1241 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24INTELLECT-3Estimated1241
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Hard reasoning
Humanity's Last ExamVerified
#96 of 19813.1%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #95Mistral Medium 3.513.8%
- #96INTELLECT-313.1%
- #97EXAONE 4.5 33B12.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~70.2%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23INTELLECT-3Estimated70.2%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#73 of 103 (estimated)~14.6
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #72Gemma 4 31B14.7
- ~#73INTELLECT-3Estimated14.6
- #73Mistral Medium 3.514.2
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#66 of 11926.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #65Ministral 3 14B27.2%
- #66INTELLECT-326.6%
- #66Llama 3.3 Instruct 70B26.6%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~55.8%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12INTELLECT-3Estimated55.8%
- #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)~42.8%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21INTELLECT-3Estimated42.8%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#58 of 92 (estimated)~720 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #57Ring-2.6-1T734
- ~#58INTELLECT-3Estimated720
- #58KAT Coder Pro V2720
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#50 of 85 (estimated)~6.2%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #49Mistral Medium 3.56.3%
- ~#50INTELLECT-3Estimated6.2%
- #50GPT-5.4 nano6.0%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#63 of 91 (estimated)~10.5%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #62Devstral 210.5%
- ~#63INTELLECT-3Estimated10.5%
- #63Nemotron 3 Super 120B A12B10.3%
No published score — estimated from related benchmarks