Ling-3.0-flash-Fin
- Input
- $0.075/M tok
- Output
- $0.22/M tok
- Blended
- $0.111/M tok · 3:1
- Speed
- 290tok/s
- Context
- 262Ktokens
- Cost per task
- ~$0.09/taskest.
Open weights (MIT); finance-tuned Ling-3.0-flash (124B total / 5.1B active MoE). Release date = OpenRouter listing; AA lists 2026-09-11. Price and speed are AA's median across hosts. Not ranked in Agents: its only agentic score is the finance-specific tau3-banking.
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
- 2× H200 141GB
- FP8 weights
- Throughput
- ~9,742 tok/s
- many requests batched
- Price
- $0.079–0.65 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Max 128GB (int4, ~170 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (124B params, 5.1B active per token) + 25% KV-cache headroom ≈ 155 GB
- 2× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~9,742 output tok/s aggregate at batch 350 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~183,349 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
~#14 of 21 (estimated)~72.1%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14Ling-3.0-flash-FinEstimated72.1%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~50.8%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Ling-3.0-flash-FinEstimated50.8%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~46.0%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Ling-3.0-flash-FinEstimated46.0%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#63 of 1010.0%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #63Ling 3.0 Tiny0.0%
- #63Ling-3.0-flash-Fin0.0%
- #63Ling-3.0-flash-VL0.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#16 of 28 (estimated)~63.3%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #15Mistral Small 464.0%
- ~#16Ling-3.0-flash-FinEstimated63.3%
- #16Claude Haiku 4.561.5%
No published score — estimated from related benchmarks
SciCodeVerified
#70 of 11842.4%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #69K2 Horizon 375B A23B42.9%
- #70Ling-3.0-flash-Fin42.4%
- #71Claude Haiku 4.542.2%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~30.0
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Ling-3.0-flash-FinEstimated30.0
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondEstimated
~#93 of 193 (estimated)~75.3%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #91NVIDIA Nemotron 3 Nano 30B A3B75.7%
- ~#93Ling-3.0-flash-FinEstimated75.3%
- #93K2 Horizon 7B75.3%
No published score — estimated from related benchmarks
Humanity's Last ExamVerified
#72 of 19822.6%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #71K2-Horizon-32B22.8%
- #72Ling-3.0-flash-Fin22.6%
- #73Qwen3.6 35B A3B22.2%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#11 of 34 (estimated)~90.4%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #10GLM-5.3-MXFP491.3%
- ~#11Ling-3.0-flash-FinEstimated90.4%
- #11Xing4.0-29B-A4B90.0%
No published score — estimated from related benchmarks