Apriel-v1.6-15B-Thinker
- Input
- —
- Output
- —
- Speed
- ~91tok/sest.
- Context
- 128Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Apriel-v1.6-15B-Thinker. 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
- 1× B200 180GB
- BF16 weights
- Throughput
- ~7,314 tok/s
- many requests batched
- Price
- $0.12–1.09 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, ~170 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (14.86B params) + 25% KV-cache headroom ≈ 37 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~7,314 output tok/s aggregate at batch 209 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~35,771 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
#39 of 13969.1%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #38Xing4.0-29B-A4B69.7%
- #39Apriel-v1.6-15B-Thinker69.1%
- #40gpt-oss-120b69.0%
artificialanalysis.ai · 2026-09-24
MMMLUEstimated
~#3 of 5 (estimated)~85.3%
- #1Gemini 3.1 Pro92.6%
- #2Gemma 4 31B88.4%
- ~#3Apriel-v1.6-15B-ThinkerEstimated85.3%
- #3Claude Haiku 4.583.0%
No published score — estimated from related benchmarks
LMArena Text, Non-English (Elo)Estimated
~#42 of 57 (estimated)~1388 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #41Claude Haiku 4.51395
- ~#42Apriel-v1.6-15B-ThinkerEstimated1388
- #42GPT-5.4 nano1387
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#42 of 57 (estimated)~1405 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #41Mistral Large 31413
- ~#42Apriel-v1.6-15B-ThinkerEstimated1405
- #42GPT-5.4 nano1402
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#18 of 26 (estimated)~1620 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #17Qwen3.8 27B1671
- ~#18Apriel-v1.6-15B-ThinkerEstimated1620
- #18Inkling1611
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#104 of 19273.3%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #103Ling 3.0 Tiny73.4%
- #104Apriel-v1.6-15B-Thinker73.3%
- #104HyperNova 60B 260573.3%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#112 of 19810.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #111NVIDIA Nemotron-Labs Dory1.0 4B10.9%
- #112Apriel-v1.6-15B-Thinker10.8%
- #112DiffusionGemma 26B A4B10.8%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~70.0%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Apriel-v1.6-15B-ThinkerEstimated70.0%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#70 of 103 (estimated)~16.3
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #69Ring-2.6-1T16.6
- ~#70Apriel-v1.6-15B-ThinkerEstimated16.3
- #70K2 Horizon 3.7B15.6
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#42 of 11969.3%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #41Nova 2.0 Lite72.8%
- #42Apriel-v1.6-15B-Thinker69.3%
- #43Nemotron 3 Super 120B A12B67.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~61.4%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Apriel-v1.6-15B-ThinkerEstimated61.4%
- #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
~#19 of 22 (estimated)~62.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Apriel-v1.6-15B-ThinkerEstimated62.0%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#36 of 92 (estimated)~1128 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #35Ling-3.0-flash-VL1150
- ~#36Apriel-v1.6-15B-ThinkerEstimated1128
- #36Nex-N2-Pro1091
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#47 of 85 (estimated)~13.5%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #46K2 Horizon 3.7B14.7%
- ~#47Apriel-v1.6-15B-ThinkerEstimated13.5%
- #47Qwen3.5 397B A17B6.9%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#50 of 91 (estimated)~14.9%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #49Mistral Medium 3.515.1%
- ~#50Apriel-v1.6-15B-ThinkerEstimated14.9%
- #50Gemma 4 31B14.8%
No published score — estimated from related benchmarks