Olmo 3 7B Instruct
- Input
- $0.10/M tok
- Output
- $0.20/M tok
- Blended
- $0.125/M tok · 3:1
- Speed
- ~100tok/sest.
- Context
- 66Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Olmo 3 7B 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
- BF16 weights
- Throughput
- ~11,326 tok/s
- many requests batched
- Price
- $0.072–0.64 /M tok
- busy → light use
- On your own machine
- RTX 5090 32GB (int4, 300+ tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- BF16 weights (7.3B params) + 25% KV-cache headroom ≈ 18 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~11,326 output tok/s aggregate at batch 256 (bandwidth-bound)
- Blended 3:1 input:output; prefill ~72,817 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
#107 of 13932.8%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #106LFM2.5-VL-1.6B33.1%
- #107Olmo 3 7B Instruct32.8%
- #108Hermes 4 - Llama-3.1 405B32.7%
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
~#52 of 57 (estimated)~1295 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #51gpt-oss-20b1299
- ~#52Olmo 3 7B InstructEstimated1295
- #52Olmo 3.1 32B Instruct1294
No published score — estimated from related benchmarks
LMArena Text (Elo)Estimated
~#52 of 57 (estimated)~1322 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #51Molmo2-8BFew votes1322
- ~#52Olmo 3 7B InstructEstimated1322
- #52Ring-flash-2.01321
No published score — estimated from related benchmarks
EQ-Bench Creative Writing v3 (Elo)Estimated
~#22 of 26 (estimated)~1431 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #21Gemini 3.1 Pro1491
- ~#22Olmo 3 7B InstructEstimated1431
- #22Mistral Large 31412
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#169 of 19240.0%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #168Gemma 4 E2B40.5%
- #169Olmo 3 7B Instruct40.0%
- #170Jamba 1.7 Large39.0%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#147 of 1985.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #147LongCat Flash Lite5.8%
- #147Olmo 3 7B Instruct5.8%
- #149Exaone 4.0 1.2B5.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#29 of 34 (estimated)~25.1%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #28Ministral 3 14B30.0%
- ~#29Olmo 3 7B InstructEstimated25.1%
- #29Ministral 3 3B22.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#100 of 103 (estimated)~5.0
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #99Ministral 3 8B5.5
- ~#100Olmo 3 7B InstructEstimated5.0
- #100Ministral 3 3B4.8
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#100 of 11912.6%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #100Jamba 1.7 Mini12.6%
- #100Olmo 3 7B Instruct12.6%
- #103Apertus 8B Instruct11.4%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#13 of 15 (estimated)~51.2%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #12Nemotron 3.5 Super VL NVFP452.3%
- ~#13Olmo 3 7B InstructEstimated51.2%
- #13Nemotron 3.5 Super VL51.1%
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)~33.2%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Olmo 3 7B InstructEstimated33.2%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#60 of 92 (estimated)~702 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #59Claude Haiku 4.5719
- ~#60Olmo 3 7B InstructEstimated702
- #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%
- ~#79Olmo 3 7B 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