Apertus 70B Instruct
- Input
- $0.82/M tok
- Output
- $2.92/M tok
- Blended
- $1.345/M tok · 3:1
- Speed
- ~75tok/sest.
- Context
- 66Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Apertus 70B Instruct. Price = AA median host price.
Rankings
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
- 1× B200 180GB
- FP8 weights
- Throughput
- ~2,313 tok/s
- many requests batched
- Price
- $0.35–3.12 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~12 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (70.6B params) + 25% KV-cache headroom ≈ 88 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~2,313 output tok/s aggregate at batch 66 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~15,058 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
#129 of 13925.9%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #128Granite 4.0 H 1B26.2%
- #129Apertus 70B Instruct25.9%
- #130Exaone 4.0 1.2B25.3%
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)Estimated
~#55 of 57 (estimated)~1273 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #54NVIDIA Nemotron 3 Nano 30B A3B1286
- ~#55Apertus 70B InstructEstimated1273
- #55Phi-41233
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#55 of 57 (estimated)~1302 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #54NVIDIA Nemotron 3 Nano 30B A3B1314
- ~#55Apertus 70B InstructEstimated1302
- #55Olmo 3.1 32B Think1286
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1413 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #21Gemini 3.1 Pro1491
- ~#22Apertus 70B InstructEstimated1413
- #22Mistral Large 31412
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#184 of 19227.2%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #183MiniCPM5-1B27.8%
- #184Apertus 70B Instruct27.2%
- #185Granite 4.0 H 1B26.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#150 of 1985.5%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #149Exaone 4.0 1.2B5.7%
- #150Apertus 70B Instruct5.5%
- #150Granite 4.0 350M5.5%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#31 of 34 (estimated)~18.8%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #30Llama 4 Maverick19.3%
- ~#31Apertus 70B InstructEstimated18.8%
- #31Falcon-H1-34B-Instruct16.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#102 of 103 (estimated)~4.5
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #100NVIDIA Nemotron 3 Nano 4B4.8
- ~#102Apertus 70B InstructEstimated4.5
- #102K2 Horizon 0.9B3.0
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#99 of 11912.9%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #98Granite 4.0 350M13.2%
- #99Apertus 70B Instruct12.9%
- #100Granite 4.0 Micro12.6%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#14 of 15 (estimated)~51.0%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #13Nemotron 3.5 Super VL51.1%
- ~#14Apertus 70B InstructEstimated51.0%
- #14Claude Haiku 4.550.7%
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)~33.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Apertus 70B InstructEstimated33.0%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~703 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60Apertus 70B InstructEstimated703
- #60MiniCPM5-2B694
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#79 of 85 (estimated)~0.3%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #77Granite 4.2 3B0.4%
- ~#79Apertus 70B InstructEstimated0.3%
- #79gpt-oss-120b0.2%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~last of 91 (estimated)below measured range (<3.3%)
No published score — estimated from related benchmarks