Favur Evals
favur.dev

Agent role · weight 14/100 · rubric v15

🔧 Code

Writes the implementation — plan → TDD implementation → self-review — against the pseudocode and architecture.

What it's scored on

Output quality
Static code quality and deliverables of the code it shipped.
Efficiency
Token volume, output per request, cost, context efficiency, request-error and hallucination rates.

Model leaderboard

Every model ranked by Code score
#ModelScore / 10CoveragenLast seen
1Qwen Plus qwen3.76.4491%42026-07-22
2Xiaomi Mimo v2.56.4288%32026-07-22
3Xiaomi Mimo Pro v2.56.3676%52026-07-26
4xAI Grok 4.56.3091%42026-07-22
5Meta Muse Spark 1.16.16100%32026-07-19
6Google Gemini Flash Lite 3.56.15100%52026-07-23
7Moonshot AI Kimi Code k2.76.1165%22026-07-10
8Google Gemini Flash Lite 3.16.0883%102026-07-19
9Google Gemini Flash 3.66.07100%22026-07-24
10Stepfun Step Flash 3.75.9283%22026-07-19
11Moonshot AI Kimi k2.65.6774%32026-07-17
12Z.ai Glm 5.25.6774%32026-07-17
13OpenAI Gpt Terra 5.65.6665%12026-07-12
14OpenAI Gpt Luna 5.65.5865%12026-07-14
15Anthropic Claude Sonnet 55.3783%42026-07-22
16DeepSeek Deepseek Flash v45.2768%62026-07-22
17Thinkingmachines Inkling5.20100%22026-07-22
18Google Gemini Pro 3.1 (preview)5.1761%22026-07-03
19Google Gemini Flash 3 (preview)5.0762%62026-07-10
20Anthropic Claude Sonnet 4.64.8161%22026-07-03
21Google Gemini Flash 3.54.7465%22026-07-08
22DeepSeek Deepseek Pro v44.5962%32026-07-05

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

Per-run history (newest first)

Every appearance of the Code role, newest first
DateRunSoWModelScore / 10
2026-07-26solarSystem__multi-xiaomi-mimo-v2.5-7.26.2026solarSystemXiaomi Mimo Pro v2.55.93
2026-07-24circles__xiaomi-multi-model-2.5-2.5-pro-7.24.2026circlesXiaomi Mimo Pro v2.56.20
2026-07-24circles__google-gemini-3.6-flash-7.23.2026circlesGoogle Gemini Flash 3.65.92
2026-07-23solarSystem/multi-anthropic-sonnet-gemini-3.5-flash-lite-7.22.2026solarSystemGoogle Gemini Flash Lite 3.55.73
2026-07-22circles__thinkingmachines-inkling-7.22.2026circlesThinkingmachines Inkling5.50
2026-07-22circles__x-ai-grok-4.5-7.22.2026circlesxAI Grok 4.56.75
2026-07-22circles__deepseek-deepseek-v4-flash-7.22.2026circlesDeepSeek Deepseek Flash v46.65
2026-07-22circles__anthropic-claude-sonnet-5-7.21.2026circlesAnthropic Claude Sonnet 55.57
2026-07-22the2048__gemini-multi-model-7-22-2026the2048Google Gemini Flash Lite 3.55.77
2026-07-22circles__qwen-qwen3.7-plus-7.22.2026circlesQwen Plus qwen3.76.70
2026-07-22circles__xiaomi-mimo-v2.5-7.22.2026circlesXiaomi Mimo v2.56.76
2026-07-21circles__google-gemini-3.6-flash-7.21.2026circlesGoogle Gemini Flash 3.66.22
2026-07-21solarSystem__google-multi-model-7.21.2026solarSystemGoogle Gemini Flash Lite 3.56.08
2026-07-21circles__x-ai-grok-4.5-7.21.2026circlesGoogle Gemini Flash Lite 3.56.59
2026-07-21circles__google-gemini-3.5-flash-lite-7.21.2026circlesGoogle Gemini Flash Lite 3.56.56
2026-07-19solarSystem__stepfun-step-3.7-flash-7.19.2026solarSystemStepfun Step Flash 3.76.12
2026-07-19circles__x-ai-grok-4.5-7.18.2026circlesxAI Grok 4.56.24
2026-07-19solarSystem__qwen-qwen3.7-plus-7.18.2026solarSystemQwen Plus qwen3.76.19
2026-07-19the2048__meta-muse-spark-1.1-7.19.2026the2048Meta Muse Spark 1.15.51
2026-07-19circles__google-gemini-3.1-flash-lite-7.19.2026circlesGoogle Gemini Flash Lite 3.15.55
2026-07-18circles__thinkingmachines-inkling-7.18.2026circlesThinkingmachines Inkling4.90
2026-07-18solarSystem__xiaomi-mimo-v2.5-7.18.2026solarSystemXiaomi Mimo v2.56.23
2026-07-17circles__z-ai-glm-5.2-7.17.2026circlesZ.ai Glm 5.26.42
2026-07-17circles__moonshotai-kimi-k2.6-7.16.2026circlesMoonshot AI Kimi k2.65.92
2026-07-17circles__x-ai-grok-4.5-7.16.2026circlesxAI Grok 4.56.71
2026-07-17circles__anthropic-claude-sonnet-5-7.16.2026circlesAnthropic Claude Sonnet 55.86
2026-07-17circles__qwen-qwen3.7-plus-7.16.2026circlesQwen Plus qwen3.75.91
2026-07-17solarSystem__meta-muse-spark-1.1-7.17.2026solarSystemMeta Muse Spark 1.15.97
2026-07-17circles__meta-muse-spark-1.1-7.16.2026circlesMeta Muse Spark 1.16.99
2026-07-16circles__google-multi-model-7.18.2026circlesGoogle Gemini Flash Lite 3.16.67
2026-07-16circles__google-multi-model-7.17.2026circlesGoogle Gemini Flash Lite 3.16.89
2026-07-15solarSystem__google-multi-model-7.15.2026solarSystemGoogle Gemini Flash Lite 3.14.27
2026-07-15circles__google-gemini-3.1-flash-lite-7.14.2026circlesGoogle Gemini Flash Lite 3.16.16
2026-07-15circles__google-multi-model-7.16.2026circlesGoogle Gemini Flash Lite 3.16.80
2026-07-15circles__google-multi-model-7.15.2026circlesGoogle Gemini Flash Lite 3.17.65
2026-07-14circles__openai-gpt-5.6-luna-7.14.2026circlesOpenAI Gpt Luna 5.65.58
2026-07-14solarSystem__google-multi-model-7.14.2026solarSystemGoogle Gemini Flash Lite 3.14.86
2026-07-13circles__stepfun-step-3.7-flash-7.13.2026circlesStepfun Step Flash 3.75.72
2026-07-13solarSystem__google-gemini-3.1-flash-lite-7.12.2026solarSystemGoogle Gemini Flash Lite 3.15.52
2026-07-12circles__openai-gpt-5.6-terra-7.11.2026circlesOpenAI Gpt Terra 5.65.66
2026-07-12circles__anthropic-claude-sonnet-5-7.11.2026circlesAnthropic Claude Sonnet 55.02
2026-07-10circles__google-gemini-3-flash-preview-7.9.2026circlesGoogle Gemini Flash 3 (preview)5.08
2026-07-10circles__moonshotai-kimi-k2.7-code-7.9.2026circlesMoonshot AI Kimi Code k2.75.69
2026-07-10circles__x-ai-grok-4.5-7.10.2026circlesxAI Grok 4.55.52
2026-07-10circles__deepseek-deepseek-v4-flash-7.10.2026circlesDeepSeek Deepseek Flash v45.87
2026-07-10circles__xiaomi-mimo-v2.5-pro-7.10.2026circlesXiaomi Mimo v2.56.27
2026-07-09circles__google-gemini-3-flash-preview-7.8.2026circlesGoogle Gemini Flash 3 (preview)5.61
2026-07-09circles__qwen-qwen3.7-plus-7.9.2026circlesQwen Plus qwen3.76.97
2026-07-09circles__google-gemini-3.1-flash-lite-7.9.2026circlesGoogle Gemini Flash Lite 3.16.43
2026-07-08circles__google-gemini-3.5-flash-7.8.2026circlesGoogle Gemini Flash 3.55.03
2026-07-08circles__google-gemini-3-flash-preview-7.7.2026circlesGoogle Gemini Flash 3 (preview)5.26
2026-07-08circles__moonshotai-kimi-k2.7-code-7.8.2026circlesMoonshot AI Kimi Code k2.76.53
2026-07-08circles__anthropic-claude-sonnet-5-7.8.2026circlesAnthropic Claude Sonnet 55.01
2026-07-05circles__google-gemini-3.5-flash-7.5.2026circlesGoogle Gemini Flash 3.54.45
2026-07-05circles__deepseek-deepseek-v4-pro-7.5.2026circlesDeepSeek Deepseek Pro v44.82
2026-07-05circles__google-gemini-3-flash-preview-7.5.2026circlesGoogle Gemini Flash 3 (preview)5.53
2026-07-05circles__moonshotai-kimi-k2.6-7.5.2026circlesMoonshot AI Kimi k2.65.12
2026-07-05circles__xiaomi-mimo-v2.5-pro-7.5.2026circlesXiaomi Mimo Pro v2.56.49
2026-07-04circles__deepseek-deepseek-v4-flash-7.3.2026circlesDeepSeek Deepseek Flash v45.08
2026-07-04circles__deepseek-deepseek-v4-flash-7.4.2026circlesDeepSeek Deepseek Flash v45.30
2026-07-03circles__anthropic-claude-sonnet-4.6-7.3.2026circlesAnthropic Claude Sonnet 4.64.95
2026-07-03circles__google-gemini-3.1-pro-preview-7.3.2026circlesGoogle Gemini Pro 3.1 (preview)4.59
2026-07-03circles__deepseek-deepseek-v4-pro-7.3.2026circlesDeepSeek Deepseek Pro v44.57
2026-07-03circles__z-ai-glm-5.2-7.3.2026circlesZ.ai Glm 5.25.72
2026-06-29solarSystem__xiaomi-mimo-v2.5-pro-6.29.2026solarSystemXiaomi Mimo Pro v2.56.27
2026-06-28circles__anthropic-claude-sonnet-4.6-6.28.2026circlesAnthropic Claude Sonnet 4.64.68
2026-06-28circles__google-gemini-3.1-pro-preview-6.28.2026circlesGoogle Gemini Pro 3.1 (preview)5.75
2026-06-28solarSystem__google-gemini-3-flash-preview-6.27.2026solarSystemGoogle Gemini Flash 3 (preview)3.53
2026-06-28circles__z-ai-glm-5.2-6.27.2026circlesZ.ai Glm 5.24.88
2026-06-28circles__xiaomi-mimo-v2.5-pro-6.28.2026circlesXiaomi Mimo Pro v2.56.93
2026-06-27circles__deepseek-deepseek-v4-pro-6.27.2026circlesDeepSeek Deepseek Pro v44.37
2026-06-27circles__moonshotai-kimi-k2.6-6.27.2026circlesMoonshot AI Kimi k2.65.96
2026-06-27solarSystem__deepseek-deepseek-v4-flash-6.27.2026solarSystemDeepSeek Deepseek Flash v44.44
2026-06-26circles__google-gemini-3-flash-preview-6.26.2026circlesGoogle Gemini Flash 3 (preview)5.40
2026-06-26the2048__deepseek-deepseek-v4-flash-6.26.2026the2048DeepSeek Deepseek Flash v44.30

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.