Ling 3.0 Flash
- Input
- $0.075/M tok
- Output
- $0.22/M tok
- Blended
- $0.111/M tok · 3:1
- Speed
- 346tok/s
- Context
- 262Ktokens
- Cost per task
- ~$0.09/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Ling 3.0 Flash. 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
- 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)~72.2%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #13Claude Haiku 4.573.3%
- ~#14Ling 3.0 FlashEstimated72.2%
- #14Nemotron 3.5 Super VL71.1%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#21 of 24 (estimated)~51.3%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #20Nemotron 3.5 Super VL51.8%
- ~#21Ling 3.0 FlashEstimated51.3%
- #21Nemotron 3.5 Super VL NVFP451.3%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~46.1%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Ling 3.0 FlashEstimated46.1%
- #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%
- #63K2 Horizon MoVA 36B A4B0.0%
- #63Ling 3.0 Flash0.0%
- #63Ling 3.0 Tiny0.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#15 of 28 (estimated)~64.9%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #14Maple-Preview75.1%
- ~#15Ling 3.0 FlashEstimated64.9%
- #15Mistral Small 464.0%
No published score — estimated from related benchmarks
SciCodeVerified
#73 of 11842.0%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #73K-EXAONE 2.0 080342.0%
- #73Ling 3.0 Flash42.0%
- #75Gemini 3.5 Flash-Lite41.3%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~30.7
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Ling 3.0 FlashEstimated30.7
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#58 of 19285.5%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #58KAT Coder Pro V285.5%
- #58Ling 3.0 Flash85.5%
- #60Ripple-65B Preview85.2%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#68 of 19823.7%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #67Nemotron 3.5 Bolt 74B-A9B24.7%
- #68Ling 3.0 Flash23.7%
- #69Gemma 4 31B23.6%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#9 of 34 (estimated)~92.7%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #8gpt-oss-120b93.4%
- ~#9Ling 3.0 FlashEstimated92.7%
- #9Qwen3.8 27B MXFP492.5%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#45 of 120 (estimated)~65.5%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #44gpt-oss-120b65.8%
- ~#45Ling 3.0 FlashEstimated65.5%
- #45Qwen3.5 0.8B65.2%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#11 of 15 (estimated)~69.0%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #10Nex-N2.5-Mini71.2%
- ~#11Ling 3.0 FlashEstimated69.0%
- #11Muse Glimmer65.9%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
No published score — estimated from related benchmarks
BrowseCompEstimated
~#18 of 22 (estimated)~71.7%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #17Beam 1.0 501B A23B76.8%
- ~#18Ling 3.0 FlashEstimated71.7%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Estimated
~#30 of 92 (estimated)~1357 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #29K2 Horizon 375B A23B1361
- ~#30Ling 3.0 FlashEstimated1357
- #30GPT-5.51336
No published score — estimated from related benchmarks
AutomationBench-AAEstimated
~#39 of 85 (estimated)~23.7%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #38Quasar 438B23.9%
- ~#39Ling 3.0 FlashEstimated23.7%
- #39MiniMax-M321.3%
No published score — estimated from related benchmarks