Trinity Large Thinking
- Input
- $0.25/M tok
- Output
- $0.80/M tok
- Blended
- $0.388/M tok · 3:1
- Speed
- 337tok/s
- Context
- 512Ktokens
- Cost per task
- ~$0.34/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Trinity Large Thinking. Price = AA median host price.
Rankings
Coding
Verified#103 / 137rank by quality32.1±8.1quality / 1002/7 benchmarks measuredWriting & chat
Verified#91 / 162rank by quality37.4±4.1quality / 1003/5 benchmarks measuredHard reasoning
Verified#126 / 218rank by quality36.5±3.7quality / 1003/4 benchmarks measuredAgents
Verified#101 / 187rank by quality29.4±4.3quality / 1004/7 benchmarks measured
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
- 8× H200 141GB
- FP8 weights
- Throughput
- ~29,038 tok/s
- many requests batched
- Price
- $0.12–0.99 /M tok
- busy → light use
- On your own machine
- Mac Studio M5 Ultra 512GB (int4, ~130 tok/s single-stream)
- single consumer GPU or Mac
Assumptions (5)
- FP8 weights (398B params, 13B active per token) + 40% KV-cache headroom ≈ 557 GB
- 8× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
- ~29,038 output tok/s aggregate at batch 1044 (bandwidth-bound); MoE compute scales with active params
- Blended 3:1 input:output; prefill ~287,716 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
~#17 of 21 (estimated)~70.2%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #16Nemotron 3 Ultra70.7%
- ~#17Trinity Large ThinkingEstimated70.2%
- #17Intern-S2-Preview (35B-A3B)64.0%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~48.5%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Trinity Large ThinkingEstimated48.5%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#38 of 46 (estimated)~44.4%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #37Qwen3.8 Max (0902)51.0%
- ~#38Trinity Large ThinkingEstimated44.4%
- #38Ripple-65B Preview44.3%
No published score — estimated from related benchmarks
Terminal-Bench 4.0Verified
#53 of 1010.5%
- #1Kimi K3.1 Pro67.2%
- #2Claude Sonnet 5.563.6%
- #53Solar Pro 40.5%
- #53Trinity Large Thinking0.5%
- #63A.X-K20.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#17 of 28 (estimated)~59.8%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #16Claude Haiku 4.561.5%
- ~#17Trinity Large ThinkingEstimated59.8%
- #17GLM-5.3 NVFP453.5%
No published score — estimated from related benchmarks
SciCodeVerified
#77 of 11840.6%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #76A.X-K241.0%
- #77Trinity Large Thinking40.6%
- #78Nemotron 3 Ultra40.3%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~28.6
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Trinity Large ThinkingEstimated28.6
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Writing & chat
IFBenchVerified
#65 of 13956.3%
- #1MiniMax-M382.9%
- #2Qwen3.8 2.4T A95B82.8%
- #64Ling-2.6-1T56.9%
- #65Trinity Large Thinking56.3%
- #66LFM2.5-8B-A1B55.6%
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)Verified
#45 of 561350 Elo
- #1Gemini 4 ArgonFew votes1512
- #2Claude Opus 5.51497
- #44GLM-4.6VFew votes1361
- #45Trinity Large Thinking1350
- #46gpt-oss-120b1338
lmarena.ai · 2026-10-08
LMArena Text (Elo)Verified
#45 of 561369 Elo
- #1Gemini 4 Argon1525
- #2Claude Opus 5.51507
- #44GLM-4.6VFew votes1378
- #45Trinity Large Thinking1369
- #46INTELLECT-31356
lmarena.ai · 2026-09-13
EQ-Bench Creative Writing v3 (Elo)Estimated
~#24 of 26 (estimated)~1329 Elo
- #1GPT-6 Astra2173
- #2Claude Fable 5.12162
- #23Gemma 4 31B1368
- ~#24Trinity Large ThinkingEstimated1329
- #24gpt-oss-120b961
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#94 of 19275.2%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #94Ling-2.6-1T75.2%
- #94Trinity Large Thinking75.2%
- #96Mistral Medium 3.574.8%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#91 of 19815.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #90KAT Coder Pro V216.1%
- #91Trinity Large Thinking15.8%
- #92Qwen3.5 9B14.9%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~67.9%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Trinity Large ThinkingEstimated67.9%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Verified
#13 of 11990.1%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #13Qwen3.8 Flash-Next NVFP490.1%
- #13Trinity Large Thinking90.1%
- #16Ling-2.6-1T89.8%
artificialanalysis.ai · 2026-09-24
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~60.6%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Trinity Large ThinkingEstimated60.6%
- #12Nemotron 3.5 Super VL NVFP452.3%
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
~#19 of 22 (estimated)~57.0%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Trinity Large ThinkingEstimated57.0%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#82 of 91324 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #81gpt-oss-20b327
- #82Trinity Large Thinking324
- #83North Mini Code299
artificialanalysis.ai · 2026-09-24