2026-09-10MODELDeepSeek-V4.1-Flash released with extreme agent memory efficiency and evaluated across VALS • 2026-09-03MODELGPT-6 Astra released by OpenAI - 71.7% on EMB, 63.3% on Tax Agent Bench • 2026-09-02MODELGoogle Gemini 3.8 Flash takes #1 rank on Finance Agent (v2) with 61.4% and 72.2% on EMB • 2026-09-02MODELMeta releases Muse Spark 1.3 & 1.3 Max - 59.0%-60.0% on Finance Agent (v2) • 2026-09-01MODELClaude Fable 5.1 leads Tax Agent Bench (77.6%) and EMB (76.7%) with 75% cheaper cache reads • 2026-09-11BENCHTax Agent Bench and FAB v2 benchmarks updated with latest frontier model rankings • 2026-09-15UPDATEPlatform updated: 43 models tracked across 41 independent benchmarks • 2026-09-10MODELDeepSeek-V4.1-Flash released with extreme agent memory efficiency and evaluated across VALS • 2026-09-03MODELGPT-6 Astra released by OpenAI - 71.7% on EMB, 63.3% on Tax Agent Bench • 2026-09-02MODELGoogle Gemini 3.8 Flash takes #1 rank on Finance Agent (v2) with 61.4% and 72.2% on EMB • 2026-09-02MODELMeta releases Muse Spark 1.3 & 1.3 Max - 59.0%-60.0% on Finance Agent (v2) • 2026-09-01MODELClaude Fable 5.1 leads Tax Agent Bench (77.6%) and EMB (76.7%) with 75% cheaper cache reads • 2026-09-11BENCHTax Agent Bench and FAB v2 benchmarks updated with latest frontier model rankings • 2026-09-15UPDATEPlatform updated: 43 models tracked across 41 independent benchmarks •
Home/Benchmarks/Vibe Code Bench v1.1
Tier 3agentTasks

Vibe Code Bench v1.1

Evaluates end-to-end full-stack frontend/backend generation and interactive software craftsmanship.

Variable tasks
23 models evaluated
Updated 2026
VALS (2026)
View Source →Submit your scoreMethodology
90.3%
Top Score
Top model
Claude Fable 5
Model Rankings
financebenchmark.ai · Vibe Code Bench
Anthropic
Anthropic
OpenAI
DeepSeek
xAI
Moonshot AI
Anthropic
DeepSeek
Google
Google
Zhipu AI
OpenAI
OpenAI
xAI
Thinking Machines
Thinking Machines
Moonshot AI
Ant Group
Meta
Meta
NVIDIA
Alibaba
Alibaba
85.0%
🥇AnthropicAnthropicClaude Opus 588.4%
🥈AnthropicAnthropicClaude Sonnet 581.3%
🥉OpenAIOpenAIGPT-5.6 Sol80.5%
4DeepSeekDeepSeekDeepSeek V4 FlashOPEN74.7%
5xAIxAIGrok 4.676.2%
6Moonshot AIMoonshot AIKimi K3OPEN85.0%
7AnthropicAnthropicClaude Fable 590.3%
8DeepSeekDeepSeekDeepSeek V4 Pro (0813)OPEN82.3%
9GoogleGoogleGemini 3.5 Flash Lite37.2%
10GoogleGoogleGemini 3.6 Flash64.0%
11Zhipu AIZhipu AIGLM 5.2OPEN64.0%
12OpenAIOpenAIGPT-5.6 Luna77.1%
13OpenAIOpenAIGPT-5.6 Terra67.8%
14xAIxAIGrok 4.569.0%
15Thinking MachinesThinking MachinesInklingOPEN19.2%
16Thinking MachinesThinking MachinesInkling SmallOPEN19.1%
17Moonshot AIMoonshot AIKimi K2.7 CodeOPEN47.2%
18Ant GroupAnt GroupLing 3.0 FlashOPEN2.9%
19MetaMetaMuse Spark 1.172.2%
20MetaMetaMuse Spark 1.279.1%
21NVIDIANVIDIANemotron 3 UltraOPEN7.6%
22AlibabaAlibabaQwen 3.7 Plus46.4%
23AlibabaAlibabaQwen 3.8 MaxOPEN64.7%
Full Results Table
#ModelOverallSourceDate
🥇
AnthropicClaude Fable 5
Anthropic
90.3VALS (2026)2026-06
🥈
AnthropicClaude Opus 5
Anthropic
88.4VALS (2026)2026-07
🥉
Moonshot AIKimi K3OPEN
Moonshot AI
85.0VALS (2026)2026-07
4
DeepSeekDeepSeek V4 Pro (0813)OPEN
DeepSeek
82.3VALS (2026)2026-08
5
AnthropicClaude Sonnet 5
Anthropic
81.3VALS (2026)2026-06
6
OpenAIGPT-5.6 Sol
OpenAI
80.5VALS (2026)2026-07
7
MetaMuse Spark 1.2
Meta
79.1VALS (2026)2026-08
8
OpenAIGPT-5.6 Luna
OpenAI
77.1VALS (2026)2026-07
9
xAIGrok 4.6
xAI
76.2VALS (2026)2026-08
10
DeepSeekDeepSeek V4 FlashOPEN
DeepSeek
74.7VALS (2026)2026-07
11
MetaMuse Spark 1.1
Meta
72.2VALS (2026)2026-07
12
xAIGrok 4.5
xAI
69.0VALS (2026)2026-07
13
OpenAIGPT-5.6 Terra
OpenAI
67.8VALS (2026)2026-07
14
AlibabaQwen 3.8 MaxOPEN
Alibaba
64.7VALS (2026)2026-08
15
GoogleGemini 3.6 Flash
Google
64.0VALS (2026)2026-07
16
Zhipu AIGLM 5.2OPEN
Zhipu AI
64.0VALS (2026)2026-06
17
Moonshot AIKimi K2.7 CodeOPEN
Moonshot AI
47.2VALS (2026)2026-06
18
AlibabaQwen 3.7 Plus
Alibaba
46.4VALS (2026)2026-06
19
GoogleGemini 3.5 Flash Lite
Google
37.2VALS (2026)2026-07
20
Thinking MachinesInklingOPEN
Thinking Machines
19.2VALS (2026)2026-07
21
Thinking MachinesInkling SmallOPEN
Thinking Machines
19.1VALS (2026)2026-07
22
NVIDIANemotron 3 UltraOPEN
NVIDIA
7.6VALS (2026)2026-06
23
Ant GroupLing 3.0 FlashOPEN
Ant Group
2.9VALS (2026)2026-07
All evaluated models
Anthropic
Claude Opus 5
88.4%
Anthropic
Claude Sonnet 5
81.3%
OpenAI
GPT-5.6 Sol
80.5%
DeepSeek
DeepSeek V4 Flash
74.7%
xAI
Grok 4.6
76.2%
Moonshot AI
Kimi K3
85.0%
Anthropic
Claude Fable 5
90.3%
DeepSeek
DeepSeek V4 Pro (0813)
82.3%
Google
Gemini 3.5 Flash Lite
37.2%
Google
Gemini 3.6 Flash
64.0%
Zhipu AI
GLM 5.2
64.0%
OpenAI
GPT-5.6 Luna
77.1%
OpenAI
GPT-5.6 Terra
67.8%
xAI
Grok 4.5
69.0%
Thinking Machines
Inkling
19.2%
Thinking Machines
Inkling Small
19.1%
Moonshot AI
Kimi K2.7 Code
47.2%
Ant Group
Ling 3.0 Flash
2.9%
Meta
Muse Spark 1.1
72.2%
Meta
Muse Spark 1.2
79.1%
NVIDIA
Nemotron 3 Ultra
7.6%
Alibaba
Qwen 3.7 Plus
46.4%
Alibaba
Qwen 3.8 Max
64.7%