Models / Deepreinforce

Ornith 1.0 35B

deepreinforce/ornith-1.0-35b

Large coding-reasoning model for agentic software tasks and RL search

Source-linkedornithOpen weightsReleased 2026-06-25

Report data

Context window262.144K

Maximum outputNot documented

Provider offers0

Knowledge cutoffUndisclosed

Capabilities

What this model supports

ReasoningYes

Tool callingYes

Structured outputNo

AttachmentsYes

Temperature controlYes

Open weightsYes

Creator: Deepreinforce
Family: ornith
Modalities: Image, Text
License: MIT
Release date: 2026-06-25
Model ID: deepreinforce/ornith-1.0-35b

Market availability

Provider pricing

Report price →

No known providers available.

Evidence

Published benchmark results

Claw-eval vs top 3 models

Ornith 1.0 397B

77.1

Ornith 1.0 35B

69.8

Ornith 1.0 9B

63.1

NL2Repo vs top 3 models

Ornith 1.0 397B

48.2

Ornith 1.0 35B

34.6

Ornith 1.0 9B

27.2

SWE-Bench Multilingual vs top 7 models

Ornith 1.0 397B

78.9

Claude Sonnet 5

78.3

Qwen3.7 Max

78.3

Grok 4.5

78.0

LongCat-2.0

77.3

Ornith 1.0 35B

69.3

Nemotron 3 Ultra 550B A55B

67.7

SWE-Bench Pro vs top 8 models

Claude Fable 5

80.3

Claude Opus 4.8

69.2

Grok 4.5

64.7

GPT-5.6 Sol

64.6

Claude Opus 4.7

64.3

GPT-5.6 Terra

63.4

Claude Sonnet 5

63.2

Ornith 1.0 35B

50.4

SWE-Bench Verified vs top 8 models

Claude Fable 5

95.0

Claude Opus 4.8

88.6

Claude Sonnet 5

85.2

Ornith 1.0 397B

82.4

DeepSeek V4 Pro

80.6

Qwen3.7 Max

80.4

Kimi K2.6

80.2

Ornith 1.0 35B

75.6

Terminal-Bench 2.1 vs top 3 models

Ornith 1.0 397B

78.2

Ornith 1.0 35B

62.8

Ornith 1.0 9B

40.6