Favur Evals
favur.dev

Agent role · weight 14/100 · rubric v15

🧭 Develop

Per-task lifecycle coordinator — sequences pseudocode, test-creation, implementation and review for each task and drives the review/verify gates.

What it's scored on

Output quality
Code quality and test quality of the task it owned, acceptance-criteria results and deliverables.
Efficiency
Token volume, cost per request and context efficiency.

Model leaderboard

Every model ranked by Develop score
#ModelScore / 10CoveragenLast seen
1Google Gemini Flash Lite 3.58.31100%12026-07-21
2Meta Muse Spark 1.17.9799%32026-07-19
3Xiaomi Mimo v2.57.8888%52026-07-26
4Google Gemini Flash 3.67.8299%52026-07-24
5xAI Grok 4.57.7585%42026-07-22
6Google Gemini Flash Lite 3.17.5355%42026-07-19
7Qwen Plus qwen3.77.4885%42026-07-22
8Stepfun Step Flash 3.76.9970%22026-07-19
9Moonshot AI Kimi Code k2.76.6340%22026-07-10
10Xiaomi Mimo Pro v2.56.4635%32026-07-05
11DeepSeek Deepseek Flash v46.4247%62026-07-22
12Google Gemini Flash 3.56.3370%82026-07-16
13OpenAI Gpt Luna 5.66.2840%12026-07-14
14OpenAI Gpt Terra 5.66.2640%12026-07-12
15Thinkingmachines Inkling6.12100%22026-07-22
16Moonshot AI Kimi k2.65.9457%32026-07-17
17DeepSeek Deepseek Pro v45.6337%32026-07-05
18Anthropic Claude Sonnet 55.6076%52026-07-23
19Z.ai Glm 5.25.4757%32026-07-17
20Google Gemini Pro 3.1 (preview)5.4636%22026-07-03
21Google Gemini Flash 3 (preview)4.8537%62026-07-10
22Anthropic Claude Sonnet 4.63.1636%22026-07-03

† low confidence — sparse role or low data coverage (renormalized, never zero-filled).

Per-run history (newest first)

Every appearance of the Develop role, newest first
DateRunSoWModelScore / 10
2026-07-26solarSystem__multi-xiaomi-mimo-v2.5-7.26.2026solarSystemXiaomi Mimo v2.57.72
2026-07-24circles__google-gemini-3.6-flash-7.23.2026circlesGoogle Gemini Flash 3.67.83
2026-07-24circles__xiaomi-multi-model-2.5-2.5-pro-7.24.2026circlesXiaomi Mimo v2.57.82
2026-07-23solarSystem/multi-anthropic-sonnet-gemini-3.5-flash-lite-7.22.2026solarSystemAnthropic Claude Sonnet 56.67
2026-07-22circles__thinkingmachines-inkling-7.22.2026circlesThinkingmachines Inkling6.55
2026-07-22circles__x-ai-grok-4.5-7.22.2026circlesxAI Grok 4.57.70
2026-07-22circles__deepseek-deepseek-v4-flash-7.22.2026circlesDeepSeek Deepseek Flash v48.06
2026-07-22circles__anthropic-claude-sonnet-5-7.21.2026circlesAnthropic Claude Sonnet 56.93
2026-07-22the2048__gemini-multi-model-7-22-2026the2048Google Gemini Flash 3.68.13
2026-07-22circles__qwen-qwen3.7-plus-7.22.2026circlesQwen Plus qwen3.77.94
2026-07-22circles__xiaomi-mimo-v2.5-7.22.2026circlesXiaomi Mimo v2.58.39
2026-07-21solarSystem__google-multi-model-7.21.2026solarSystemGoogle Gemini Flash 3.68.03
2026-07-21circles__x-ai-grok-4.5-7.21.2026circlesGoogle Gemini Flash 3.67.69
2026-07-21circles__google-gemini-3.6-flash-7.21.2026circlesGoogle Gemini Flash 3.67.44
2026-07-21circles__google-gemini-3.5-flash-lite-7.21.2026circlesGoogle Gemini Flash Lite 3.58.31
2026-07-19solarSystem__stepfun-step-3.7-flash-7.19.2026solarSystemStepfun Step Flash 3.77.10
2026-07-19circles__x-ai-grok-4.5-7.18.2026circlesxAI Grok 4.58.07
2026-07-19circles__google-gemini-3.1-flash-lite-7.19.2026circlesGoogle Gemini Flash Lite 3.17.96
2026-07-19solarSystem__qwen-qwen3.7-plus-7.18.2026solarSystemQwen Plus qwen3.77.20
2026-07-19the2048__meta-muse-spark-1.1-7.19.2026the2048Meta Muse Spark 1.17.25
2026-07-18circles__thinkingmachines-inkling-7.18.2026circlesThinkingmachines Inkling5.69
2026-07-18solarSystem__xiaomi-mimo-v2.5-7.18.2026solarSystemXiaomi Mimo v2.58.41
2026-07-17circles__z-ai-glm-5.2-7.17.2026circlesZ.ai Glm 5.27.56
2026-07-17circles__moonshotai-kimi-k2.6-7.16.2026circlesMoonshot AI Kimi k2.67.73
2026-07-17circles__x-ai-grok-4.5-7.16.2026circlesxAI Grok 4.58.11
2026-07-17circles__anthropic-claude-sonnet-5-7.16.2026circlesAnthropic Claude Sonnet 57.42
2026-07-17circles__qwen-qwen3.7-plus-7.16.2026circlesQwen Plus qwen3.78.15
2026-07-17solarSystem__meta-muse-spark-1.1-7.17.2026solarSystemMeta Muse Spark 1.18.10
2026-07-17circles__meta-muse-spark-1.1-7.16.2026circlesMeta Muse Spark 1.18.56
2026-07-16circles__google-multi-model-7.18.2026circlesGoogle Gemini Flash 3.57.89
2026-07-16circles__google-multi-model-7.17.2026circlesGoogle Gemini Flash 3.58.10
2026-07-15circles__google-gemini-3.1-flash-lite-7.14.2026circlesGoogle Gemini Flash Lite 3.16.95
2026-07-15solarSystem__google-multi-model-7.15.2026solarSystemGoogle Gemini Flash 3.55.33
2026-07-15circles__google-multi-model-7.16.2026circlesGoogle Gemini Flash 3.57.74
2026-07-15circles__google-multi-model-7.15.2026circlesGoogle Gemini Flash 3.57.84
2026-07-14circles__openai-gpt-5.6-luna-7.14.2026circlesOpenAI Gpt Luna 5.66.28
2026-07-14solarSystem__google-multi-model-7.14.2026solarSystemGoogle Gemini Flash 3.55.20
2026-07-13circles__stepfun-step-3.7-flash-7.13.2026circlesStepfun Step Flash 3.76.88
2026-07-13solarSystem__google-gemini-3.1-flash-lite-7.12.2026solarSystemGoogle Gemini Flash Lite 3.17.64
2026-07-12circles__openai-gpt-5.6-terra-7.11.2026circlesOpenAI Gpt Terra 5.66.26
2026-07-12circles__anthropic-claude-sonnet-5-7.11.2026circlesAnthropic Claude Sonnet 53.22
2026-07-10circles__google-gemini-3-flash-preview-7.9.2026circlesGoogle Gemini Flash 3 (preview)5.25
2026-07-10circles__moonshotai-kimi-k2.7-code-7.9.2026circlesMoonshot AI Kimi Code k2.76.72
2026-07-10circles__x-ai-grok-4.5-7.10.2026circlesxAI Grok 4.57.12
2026-07-10circles__deepseek-deepseek-v4-flash-7.10.2026circlesDeepSeek Deepseek Flash v47.55
2026-07-10circles__xiaomi-mimo-v2.5-pro-7.10.2026circlesXiaomi Mimo v2.57.05
2026-07-09circles__google-gemini-3-flash-preview-7.8.2026circlesGoogle Gemini Flash 3 (preview)5.26
2026-07-09circles__google-gemini-3.1-flash-lite-7.9.2026circlesGoogle Gemini Flash Lite 3.17.58
2026-07-09circles__qwen-qwen3.7-plus-7.9.2026circlesQwen Plus qwen3.76.64
2026-07-08circles__google-gemini-3-flash-preview-7.7.2026circlesGoogle Gemini Flash 3 (preview)4.40
2026-07-08circles__moonshotai-kimi-k2.7-code-7.8.2026circlesMoonshot AI Kimi Code k2.76.54
2026-07-08circles__anthropic-claude-sonnet-5-7.8.2026circlesAnthropic Claude Sonnet 53.74
2026-07-08circles__google-gemini-3.5-flash-7.8.2026circlesGoogle Gemini Flash 3.54.43
2026-07-05circles__deepseek-deepseek-v4-pro-7.5.2026circlesDeepSeek Deepseek Pro v46.14
2026-07-05circles__google-gemini-3-flash-preview-7.5.2026circlesGoogle Gemini Flash 3 (preview)5.10
2026-07-05circles__moonshotai-kimi-k2.6-7.5.2026circlesMoonshot AI Kimi k2.64.66
2026-07-05circles__xiaomi-mimo-v2.5-pro-7.5.2026circlesXiaomi Mimo Pro v2.57.09
2026-07-05circles__google-gemini-3.5-flash-7.5.2026circlesGoogle Gemini Flash 3.54.11
2026-07-04circles__deepseek-deepseek-v4-flash-7.3.2026circlesDeepSeek Deepseek Flash v46.09
2026-07-04circles__deepseek-deepseek-v4-flash-7.4.2026circlesDeepSeek Deepseek Flash v46.19
2026-07-03circles__anthropic-claude-sonnet-4.6-7.3.2026circlesAnthropic Claude Sonnet 4.63.57
2026-07-03circles__google-gemini-3.1-pro-preview-7.3.2026circlesGoogle Gemini Pro 3.1 (preview)5.25
2026-07-03circles__deepseek-deepseek-v4-pro-7.3.2026circlesDeepSeek Deepseek Pro v45.24
2026-07-03circles__z-ai-glm-5.2-7.3.2026circlesZ.ai Glm 5.25.33
2026-06-29solarSystem__xiaomi-mimo-v2.5-pro-6.29.2026solarSystemXiaomi Mimo Pro v2.56.23
2026-06-28circles__anthropic-claude-sonnet-4.6-6.28.2026circlesAnthropic Claude Sonnet 4.62.74
2026-06-28circles__google-gemini-3.1-pro-preview-6.28.2026circlesGoogle Gemini Pro 3.1 (preview)5.68
2026-06-28solarSystem__google-gemini-3-flash-preview-6.27.2026solarSystemGoogle Gemini Flash 3 (preview)3.46
2026-06-28circles__z-ai-glm-5.2-6.27.2026circlesZ.ai Glm 5.23.53
2026-06-28circles__xiaomi-mimo-v2.5-pro-6.28.2026circlesXiaomi Mimo Pro v2.56.05
2026-06-27circles__deepseek-deepseek-v4-pro-6.27.2026circlesDeepSeek Deepseek Pro v45.52
2026-06-27circles__moonshotai-kimi-k2.6-6.27.2026circlesMoonshot AI Kimi k2.65.44
2026-06-27solarSystem__deepseek-deepseek-v4-flash-6.27.2026solarSystemDeepSeek Deepseek Flash v44.95
2026-06-26circles__google-gemini-3-flash-preview-6.26.2026circlesGoogle Gemini Flash 3 (preview)5.65
2026-06-26the2048__deepseek-deepseek-v4-flash-6.26.2026the2048DeepSeek Deepseek Flash v45.68

Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded — no vendor sponsorship, credits, or grants.