Skip to content
Model Pareto

Mercury 2.5

InceptionProprietaryinceptionlabs.ai ↗
Compare with nearest rivalsCompare with…
Input
$0.20/M tok
Output
$0.75/M tok
Blended
$0.338/M tok · 3:1
Speed
781tok/s
Context
260Ktokens

Diffusion LLM; vendor claims 1,107 tok/s. Launch discount $0.04/$0.15 (80% off).

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench Pro (Public)Estimated
~#18 of 19 (estimated)~49.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #17Muse Glimmer51.2%
  4. ~#18Mercury 2.5Estimated49.1%
  5. #18Nex-N2.5-Mini43.8%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#28 of 31 (estimated)~46.0%
  1. #1DeepSeek V4.1 Flash74.2%
  2. #2Grok 4.772.6%
  3. #27Qwen3.8 Max (0902)51.0%
  4. ~#28Mercury 2.5Estimated46.0%
  5. #28Qwen3.8 27B42.2%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#10 of 20 (estimated)~55.7%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #9Claude Haiku 4.561.5%
  4. ~#10Mercury 2.5Estimated55.7%
  5. #10Phi-4-reasoning-plus53.1%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~last of 15 (estimated)below measured range (<41.1)
  1. #1Claude Opus 5.566.0
  2. #2Claude Fable 5.162.2
  3. #14GPT-6 Luna41.1
  4. ~#15Mercury 2.5Estimated<41.1
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#113 of 173 (estimated)~62.9%
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. #111Granite 4.2 8B63.1%
  4. ~#113Mercury 2.5Estimated62.9%
  5. #113EXAONE 4.0 32B62.8%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#14 of 25 (estimated)~61.5%
  1. #1Inkling97.1%
  2. #2Muse Glimmer94.7%
  3. #13Phi-4-reasoning-plus78.0%
  4. ~#14Mercury 2.5Estimated61.5%
  5. #14Mistral Large 338.0%
No published score — estimated from related benchmarks

Agents

τ²-bench (Telecom)Estimated
~#54 of 116 (estimated)~34.5%
  1. #1Step 3.7 Flash98.5%
  2. #2Gemini 3.1 Pro95.6%
  3. #53North Mini Code37.4%
  4. ~#54Mercury 2.5Estimated34.5%
  5. #54Sarvam 30B34.5%
No published score — estimated from related benchmarks
OSWorld-VerifiedEstimated
~#11 of 12 (estimated)~61.7%
  1. #1Kimi K384.8%
  2. #2Qwen3.8 27B84.3%
  3. #10Muse Glimmer65.9%
  4. ~#11Mercury 2.5Estimated61.7%
  5. #11Claude Haiku 4.550.7%
No published score — estimated from related benchmarks
OSWorld 2.0Estimated
~last of 5 (estimated)below measured range (<47.5%)
  1. #1GLM-5.3 Flash59.1%
  2. #2Kimi K358.3%
  3. #4GPT-5.547.5%
  4. ~#5Mercury 2.5Estimated<47.5%
No published score — estimated from related benchmarks
BrowseCompEstimated
~#15 of 18 (estimated)~56.5%
  1. #1Atria Dawn Preview92.5%
  2. #2GPT-6 Astra91.5%
  3. #14Inkling77.1%
  4. ~#15Mercury 2.5Estimated56.5%
  5. #15Mistral Medium 3.548.6%
No published score — estimated from related benchmarks
τ-Bench Banking (AA)Estimated
~#60 of 89 (estimated)~10.6%
  1. #1Muse Spark 1.350.5%
  2. #2GLM-5.350.3%
  3. #59Devstral Small 210.7%
  4. ~#60Mercury 2.5Estimated10.6%
  5. #60Devstral 210.5%
No published score — estimated from related benchmarks