Celeris-1
- Input
- $0.20/M tok
- Output
- $0.70/M tok
- Blended
- $0.325/M tok · 3:1
- Speed
- 1521tok/s
- Context
- 131Ktokens
- Cost per task
- ~$0.29/taskest.
Long-tail import from Artificial Analysis (2026-09-24); AA variant: Celeris-1. Price = AA median host price.
Rankings
Benchmark scores
~ italic, dashed = no published score yet, estimated from related benchmarks.
Coding
SWE-bench VerifiedEstimated
~#19 of 21 (estimated)~59.8%
- #1Claude Opus 596.0%
- #2Claude Sonnet 585.2%
- #18gpt-oss-120b62.4%
- ~#19Celeris-1Estimated59.8%
- #19NVIDIA Nemotron-Labs Dory1.0 4B59.5%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#23 of 24 (estimated)~45.4%
- #1Claude Fable 5.293.0%
- #2Claude Opus 5.589.9%
- #22Muse Glimmer51.2%
- ~#23Celeris-1Estimated45.4%
- #23Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#43 of 46 (estimated)~32.7%
- #1Gemini 4 Argon78.8%
- #2DeepSeek V4.1 Flash 101777.0%
- #42Nex-N2.5-Mini36.1%
- ~#43Celeris-1Estimated32.7%
- #43Hy328.0%
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%
- #63Apodex 1.10.0%
- #63Celeris-10.0%
- #63Claude Haiku 4.50.0%
artificialanalysis.ai · 2026-09-24
LiveCodeBenchEstimated
~#22 of 28 (estimated)~42.0%
- #1Qwen3.8-Omni-Flash92.6%
- #2Qwen3.8 Flash-Next91.9%
- #21Devstral 244.8%
- ~#22Celeris-1Estimated42.0%
- #22Llama 4 Maverick39.7%
No published score — estimated from related benchmarks
SciCodeVerified
#112 of 11821.6%
- #1Claude Fable 5.267.7%
- #2Claude Opus 5.566.9%
- #111K2 Horizon 3.7B22.0%
- #112Celeris-121.6%
- #113Llama 4 Scout21.3%
artificialanalysis.ai · 2026-09-24
AA Coding Agent IndexEstimated
~#25 of 26 (estimated)~27.9
- #1Claude Opus 5.561.7
- #2Claude Opus 559.7
- #24GPT-6 Luna31.1
- ~#25Celeris-1Estimated27.9
- #25Muse Spark Open26.3
No published score — estimated from related benchmarks
Hard reasoning
GPQA DiamondVerified
#131 of 19263.1%
- #1GPT-6 Astra96.1%
- #2Gemini 3.8 Flash95.3%
- #130Sarvam 30B63.3%
- #131Celeris-163.1%
- #131Granite 4.2 8B63.1%
artificialanalysis.ai · 2026-09-24
Humanity's Last ExamVerified
#135 of 1986.8%
- #1Claude Fable 5.274.3%
- #2Claude Opus 5.561.4%
- #134LFM2.5-8B-A1B6.9%
- #135Celeris-16.8%
- #136LFM2.5-1.2B-Instruct6.7%
artificialanalysis.ai · 2026-09-24
AIME (latest)Estimated
~#23 of 34 (estimated)~47.1%
- #1GLM-5.3 NVFP499.5%
- #2Beam 1.0 501B A23B97.7%
- #22Phi-4-reasoning-plus78.0%
- ~#23Celeris-1Estimated47.1%
- #23Mistral Large 338.0%
No published score — estimated from related benchmarks
Agents
τ²-bench (Telecom)Estimated
~#59 of 120 (estimated)~34.0%
- #1Step 3.7 Flash98.5%
- #2DeepSeek-V4-Pro-0813-nvfp4-DSpark98.3%
- #58Sarvam 30B34.5%
- ~#59Celeris-1Estimated34.0%
- #59Gemma 4 12B31.9%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#12 of 15 (estimated)~57.7%
- #1Kimi K384.8%
- #2Qwen3.8 27B84.3%
- #11Muse Glimmer65.9%
- ~#12Celeris-1Estimated57.7%
- #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)~51.7%
- #1Atria Dawn Preview92.5%
- #2GPT-6 Astra91.5%
- #18Nemotron 3.5 Bolt 74B-A9B70.0%
- ~#19Celeris-1Estimated51.7%
- #19Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
GDPval-AA (Elo)Verified
#84 of 91288 Elo
- #1Claude Opus 5.51866
- #2Muse Wonder Full1857
- #83North Mini Code299
- #84Celeris-1288
- #85Nemotron Cascade 2 30B A3B252
artificialanalysis.ai · 2026-09-24
AutomationBench-AAVerified
#77 of 840.4%
- #1Claude Fable 5.276.4%
- #2Muse Wonder Full71.3%
- #76Ministral 3 8B0.5%
- #77Celeris-10.4%
- #77Granite 4.2 3B0.4%
artificialanalysis.ai · 2026-09-24