Skip to content
Model Pareto

Solar Open2 250B

UpstageOpen weightsartificialanalysis.ai ↗
Compare with nearest rivalsCompare with…
Input
—
Output
—
Speed
~94tok/sest.
Context
1Mtokens

Long-tail import from Artificial Analysis (2026-09-24); AA variant: Solar Open2 250B. 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
4× B200 180GB
FP8 weights
Throughput
~21,909 tok/s
many requests batched
Price
$0.12–1.11 /M tok
busy → light use
On your own machine
Mac Studio M5 Ultra 512GB (int4, ~110 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (250B params, 15B active per token) + 40% KV-cache headroom ≈ 350 GB
  • 4× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
  • ~21,909 output tok/s aggregate at batch 627 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~283,500 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.

Coding

SWE-bench VerifiedEstimated
~#5 of 14 (estimated)~78.3%
  1. #1Claude Opus 596.0%
  2. #2Claude Sonnet 585.2%
  3. #4MiniMax-M380.5%
  4. ~#5Solar Open2 250BEstimated78.3%
  5. #5Hy378.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#13 of 19 (estimated)~58.3%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #12GPT-5.558.6%
  4. ~#13Solar Open2 250BEstimated58.3%
  5. #13Hy357.9%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#27 of 31 (estimated)~53.8%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #26Nex-N2.5-Pro55.8%
  4. ~#27Solar Open2 250BEstimated53.8%
  5. #27Qwen3.8 Max (0902)51.0%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Estimated
~#21 of 84 (estimated)~14.2%
  1. #1Claude Sonnet 5.563.6%
  2. #2Claude Opus 5.559.6%
  3. #20GPT-5.514.6%
  4. ~#21Solar Open2 250BEstimated14.2%
  5. #21Claude Sonnet 514.1%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#6 of 20 (estimated)~82.9%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #5gpt-oss-120b87.8%
  4. ~#6Solar Open2 250BEstimated82.9%
  5. #6Gemma 4 31B80.0%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Solar Open2 250BEstimated<41.1
No published score — estimated from related benchmarks

Hard reasoning

AIME (latest)Estimated
~#2 of 25 (estimated)~96.2%
  1. #1Inkling97.1%
  2. ~#2Solar Open2 250BEstimated96.2%
  3. #2Muse Glimmer94.7%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#29 of 75 (estimated)~27.7
  1. #1Claude Opus 5.557.6
  2. #2Claude Sonnet 5.556.0
  3. #28MiniMax-M329.2
  4. ~#29Solar Open2 250BEstimated27.7
  5. #29Quasar 438B26.7
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#24 of 116 (estimated)~86.0%
  1. #1Step 3.7 Flash98.5%
  2. #2Gemini 3.1 Pro95.6%
  3. #23GPT-5.3 Codex86.0%
  4. ~#24Solar Open2 250BEstimated86.0%
  5. #24GPT-5.4 mini83.3%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#10 of 12 (estimated)~70.0%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #9Nex-N2.5-Mini71.2%
  4. ~#10Solar Open2 250BEstimated70.0%
  5. #10Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Solar Open2 250BEstimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~68.7%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Solar Open2 250BEstimated68.7%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#23 of 87 (estimated)~1371 Elo
  1. #1Claude Opus 5.51846
  2. #2Claude Fable 5.11735
  3. #22Qwen3.8 27B1409
  4. ~#23Solar Open2 250BEstimated1371
  5. #23GPT-6 Luna1367
No published score — estimated from related benchmarks