Ring-flash-2.0
- Input
- $0.14/M tok
- Output
- $0.57/M tok
- Blended
- $0.247/M tok · 3:1
- Speed
- ~130tok/sest.
- Context
- 128Ktokens
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Ring-flash-2.0. 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
- ~5,348 tok/s
- many requests batched
- Price
- $0.11–1.01 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~140 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (100B params, 6.1B active per token) + 25% KV-cache headroom ≈ 125 GB
- 1× B200 180GB at $5.98–$14.24/GPU-hour on-demand (2026-09-24)
- ~5,348 output tok/s aggregate at batch 153 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~174,283 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
#83 of 13943.3%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #82LFM2.5-1.2B-Instruct43.8%
- #83Ring-flash-2.043.3%
- #84LongCat Flash Lite43.1%
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
#53 of 561293 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #52Olmo 3.1 32B Instruct1294
- #53Ring-flash-2.0Few votes1293
- #54NVIDIA Nemotron 3 Nano 30B A3B1286
lmarena.ai · 2026-09-13
LMArena Text (Elo)Verified
#52 of 561321 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #51Molmo2-8BFew votes1322
- #52Ring-flash-2.01321
- #53gpt-oss-20b1317
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1281 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24Ring-flash-2.0Estimated1281
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#109 of 19272.5%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #108Hermes 4 - Llama-3.1 405B72.7%
- #109Ring-flash-2.072.5%
- #110NVIDIA Nemotron-Labs Dory1.0 4B72.4%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#123 of 1989.6%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #122Granite 4.2 8B9.7%
- #123Ring-flash-2.09.6%
- #124Nova 2.0 Pro Preview9.4%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~62.5%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Ring-flash-2.0Estimated62.5%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
AA Intelligence IndexEstimated
~#85 of 103 (estimated)~11.0
- #1Gemini 4 Carbon59.4
- #2Claude Opus 5.557.6
- #83Ling 3.0 Tiny11.1
- ~#85Ring-flash-2.0Estimated11.0
- #85Trinity Large Thinking10.8
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#110 of 1190.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #110Reka Flash 30.0%
- #110Ring-flash-2.00.0%
- #110Tiny Aya Global0.0%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~54.2%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Ring-flash-2.0Estimated54.2%
- #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)~38.5%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #20Nemotron 3 Ultra44.4%
- ~#21Ring-flash-2.0Estimated38.5%
- #21Mistral Small 421.3%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#63 of 92 (estimated)~603 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #62Gemma 4 31B606
- ~#63Ring-flash-2.0Estimated603
- #63gpt-oss-120b596
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#62 of 85 (estimated)~2.1%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #61Mercury 2.52.4%
- ~#62Ring-flash-2.0Estimated2.1%
- #62Granite 4.2 8B2.1%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#69 of 91 (estimated)~7.4%
- #1Muse Spark 1.350.5%
- #2GLM-5.350.3%
- #68Granite 4.2 8B7.6%
- ~#69Ring-flash-2.0Estimated7.4%
- #69LFM2.5-2.6B7.2%
No published score — estimated from related benchmarks