FlavourBench Complete Core
Version complete core
Models choose three of eight ingredients for pairing, substitution, or a culinary constraint. A fixed scoring function assigns each possible combination a value from zero to 100.
The authors publish 27 model scores on the same 534 tasks. The scores measure agreement with Epicure’s ingredient rankings.
- Made by
- Josef Chen and Erim Hayretci
- Released
- August 2026
- Kind
- Taste and style
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
Grok 4.6 leads with 65.1 among models released by August 2026 Grok 4.6 leads with 65.1 among models released by August 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 14 more
- 65.1 Grok 4.6
- 65.0
Gemini 3.1 Pro
- 64.2 GPT-5.6 Sol Pro
- 63.8
Muse Spark 1.2
- 63.7 GPT-5.6 Terra Pro
- 63.4 Claude Fable 5
- 62.6 GPT-5.6 Luna
- 62.5 Claude Opus 5
- 62.1
Qwen3.8-2.4T-A95B
- 62.0 Kimi K3
- 62.0
Gemini 3.6 Flash
- 62.0
DeepSeek V4 Pro 0813
- 61.5
Qwen 3.8 Max
- 61.5
Tencent Hy3
- 60.9
MiniMax-M3
- 60.6 GLM-5.3
- 59.9
Muse Glimmer
- 59.7 Seed 2.1 Turbo
- 59.6
Inkling
- 59.5 Claude Sonnet 5
- 58.5 GLM-5.2
- 57.4
Nemotron 3.5 Lightning 30B-A3B
- 56.7
Cohere Command A
- 55.4
DeepSeek V4 Flash 0731
- 55.4
Mistral Large 3
- 53.6
Llama 4 Maverick
- 47.9 Command R+ (08-2024)
- 1 Grok 4.6 minimal 65.1
- 2
Gemini 3.1 Pro minimal 65.0
- 3 GPT-5.6 Sol Pro minimal 64.2
- 4
Muse Spark 1.2 minimal 63.8
- 5 GPT-5.6 Terra Pro minimal 63.7
- 6 Claude Fable 5 minimal 63.4
- 7 GPT-5.6 Luna pro, minimal 62.6
- 8 Claude Opus 5 minimal 62.5
- 9
Qwen3.8-2.4T-A95B low 62.1
- 10 Kimi K3 low 62.0
- 11
Gemini 3.6 Flash minimal 62.0
- 12
DeepSeek V4 Pro 0813 minimal 62.0
- 13
Qwen 3.8 Max minimal 61.5
- 14
Tencent Hy3 minimal 61.5
- 15
MiniMax-M3 provider_fixed 60.9
- 16 GLM-5.3 provider_fixed 60.6
- 17
Muse Glimmer minimal 59.9
- 18 Seed 2.1 Turbo none 59.7
- 19
Inkling minimal 59.6
- 20 Claude Sonnet 5 minimal 59.5
- 21 GLM-5.2 none 58.5
- 22
Nemotron 3.5 Lightning 30B-A3B provider_fixed 57.4
- 23
Cohere Command A provider_fixed 56.7
- 24
DeepSeek V4 Flash 0731 none 55.4
- 25
Mistral Large 3 provider_fixed 55.4
- 26
Llama 4 Maverick provider_fixed 53.6
- 27 Command R+ (08-2024) provider_fixed 47.9
Source: Official FlavourBench Complete Core leaderboard
- 65.1 Grok 4.6
- 65.0
Gemini 3.1 Pro
- 64.2 GPT-5.6 Sol Pro
- 63.8
Muse Spark 1.2
- 63.4 Claude Fable 5
- 62.6 GPT-5.6 Luna
- 62.5 Claude Opus 5
- 62.1
Qwen3.8-2.4T-A95B
- 62.0 Kimi K3
- 62.0
Gemini 3.6 Flash
- 62.0
DeepSeek V4 Pro 0813
- 61.5
Qwen 3.8 Max
- 61.5
Tencent Hy3
- 60.9
MiniMax-M3
- 60.6 GLM-5.3
- 59.9
Muse Glimmer
- 59.6
Inkling
- 59.5 Claude Sonnet 5
- 58.5 GLM-5.2
- 57.4
Nemotron 3.5 Lightning 30B-A3B
- 56.7
Cohere Command A
- 55.4
DeepSeek V4 Flash 0731
- 55.4
Mistral Large 3
- 53.6
Llama 4 Maverick
- 1 Grok 4.6 minimal 65.1
- 2
Gemini 3.1 Pro minimal 65.0
- 3 GPT-5.6 Sol Pro minimal 64.2
- 4
Muse Spark 1.2 minimal 63.8
- 5 Claude Fable 5 minimal 63.4
- 6 GPT-5.6 Luna pro, minimal 62.6
- 7 Claude Opus 5 minimal 62.5
- 8
Qwen3.8-2.4T-A95B low 62.1
- 9 Kimi K3 low 62.0
- 10
Gemini 3.6 Flash minimal 62.0
- 11
DeepSeek V4 Pro 0813 minimal 62.0
- 12
Qwen 3.8 Max minimal 61.5
- 13
Tencent Hy3 minimal 61.5
- 14
MiniMax-M3 provider_fixed 60.9
- 15 GLM-5.3 provider_fixed 60.6
- 16
Muse Glimmer minimal 59.9
- 17
Inkling minimal 59.6
- 18 Claude Sonnet 5 minimal 59.5
- 19 GLM-5.2 none 58.5
- 20
Nemotron 3.5 Lightning 30B-A3B provider_fixed 57.4
- 21
Cohere Command A provider_fixed 56.7
- 22
DeepSeek V4 Flash 0731 none 55.4
- 23
Mistral Large 3 provider_fixed 55.4
- 24
Llama 4 Maverick provider_fixed 53.6
Source: Official FlavourBench Complete Core leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.6 | 65.1 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 2 | | 65.0 ±4.1 | minimal, openrouter | Feb 2026 | Official leaderboard |
| 3 | GPT-5.6 Sol Pro | 64.2 ±4.1 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 4 | | 63.8 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 5 | GPT-5.6 Terra Pro | 63.7 ±4.1 | minimal, openrouter | Official leaderboard | |
| 6 | Claude Fable 5 | 63.4 ±4.2 | minimal, openrouter | Jun 2026 | Official leaderboard |
| 7 | GPT-5.6 Luna | 62.6 ±4.1 | pro, minimal, openrouter | Jul 2026 | Official leaderboard |
| 8 | Claude Opus 5 | 62.5 ±4.1 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 9 | | 62.1 ±4.2 | low, openrouter | Aug 2026 | Official leaderboard |
| 10 | Kimi K3 | 62.0 ±4.1 | low, openrouter | Jul 2026 | Official leaderboard |
| 11 | | 62.0 ±4.3 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 12 | | 62.0 ±4.2 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 13 | | 61.5 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 14 | | 61.5 ±4.2 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 15 | | 60.9 ±4.2 | provider_fixed, openrouter | Jun 2026 | Official leaderboard |
| 16 | GLM-5.3 | 60.6 ±4.2 | provider_fixed, zai_coding_direct | Aug 2026 | Official leaderboard |
| 17 | | 59.9 ±4 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 18 | Seed 2.1 Turbo | 59.7 ±4.3 | none, openrouter | Official leaderboard | |
| 19 | | 59.6 ±4.2 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 20 | Claude Sonnet 5 | 59.5 ±4.1 | minimal, openrouter | Jun 2026 | Official leaderboard |
| 21 | GLM-5.2 | 58.5 ±4.3 | none, openrouter | Jun 2026 | Official leaderboard |
| 22 | | 57.4 ±4.2 | provider_fixed, openrouter | Aug 2026 | Official leaderboard |
| 23 | | 56.7 ±4.2 | provider_fixed, openrouter | Mar 2025 | Official leaderboard |
| 24 | | 55.4 ±4.3 | none, openrouter | Jul 2026 | Official leaderboard |
| 25 | | 55.4 ±4.1 | provider_fixed, openrouter | Dec 2025 | Official leaderboard |
| 26 | | 53.6 ±4 | provider_fixed, openrouter | Apr 2025 | Official leaderboard |
| 27 | Command R+ (08-2024) | 47.9 ±4.1 | provider_fixed, openrouter | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Grok 4.6 | 65.1 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 2 | | 65.0 ±4.1 | minimal, openrouter | Feb 2026 | Official leaderboard |
| 3 | GPT-5.6 Sol Pro | 64.2 ±4.1 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 4 | | 63.8 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 5 | Claude Fable 5 | 63.4 ±4.2 | minimal, openrouter | Jun 2026 | Official leaderboard |
| 6 | GPT-5.6 Luna | 62.6 ±4.1 | pro, minimal, openrouter | Jul 2026 | Official leaderboard |
| 7 | Claude Opus 5 | 62.5 ±4.1 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 8 | | 62.1 ±4.2 | low, openrouter | Aug 2026 | Official leaderboard |
| 9 | Kimi K3 | 62.0 ±4.1 | low, openrouter | Jul 2026 | Official leaderboard |
| 10 | | 62.0 ±4.3 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 11 | | 62.0 ±4.2 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 12 | | 61.5 ±4.1 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 13 | | 61.5 ±4.2 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 14 | | 60.9 ±4.2 | provider_fixed, openrouter | Jun 2026 | Official leaderboard |
| 15 | GLM-5.3 | 60.6 ±4.2 | provider_fixed, zai_coding_direct | Aug 2026 | Official leaderboard |
| 16 | | 59.9 ±4 | minimal, openrouter | Aug 2026 | Official leaderboard |
| 17 | | 59.6 ±4.2 | minimal, openrouter | Jul 2026 | Official leaderboard |
| 18 | Claude Sonnet 5 | 59.5 ±4.1 | minimal, openrouter | Jun 2026 | Official leaderboard |
| 19 | GLM-5.2 | 58.5 ±4.3 | none, openrouter | Jun 2026 | Official leaderboard |
| 20 | | 57.4 ±4.2 | provider_fixed, openrouter | Aug 2026 | Official leaderboard |
| 21 | | 56.7 ±4.2 | provider_fixed, openrouter | Mar 2025 | Official leaderboard |
| 22 | | 55.4 ±4.3 | none, openrouter | Jul 2026 | Official leaderboard |
| 23 | | 55.4 ±4.1 | provider_fixed, openrouter | Dec 2025 | Official leaderboard |
| 24 | | 53.6 ±4 | provider_fixed, openrouter | Apr 2025 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Constraint, Pairing and Substitution. Grok 4.6 leads 2 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Constraint
24 models we track have a score here.
- 1 Grok 4.6 58.2
- 2
Muse Spark 1.2 ↑2 55.0
- 3
Gemini 3.1 Pro ↓1 54.2
- 4 GPT-5.6 Sol Pro ↓1 54.1
- 5 GPT-5.6 Luna ↑1 53.7
- 6
Qwen3.8-2.4T-A95B ↑2 52.5
- 7
Gemini 3.6 Flash ↑3 51.6
- 8 Claude Fable 5 ↓3 51.3
- 9
Tencent Hy3 ↑4 50.5
- 10 Claude Opus 5 ↓3 50.4
Pairing
24 models we track have a score here.
- 1 Kimi K3 ↑8 73.7
- 2 GPT-5.6 Sol Pro ↑1 72.5
- 3
Gemini 3.1 Pro ↓1 71.6
- 4 Grok 4.6 ↓3 70.9
- 5 Claude Fable 5 70.6
- 6
Muse Spark 1.2 ↓2 70.3
- 7
MiniMax-M3 ↑7 69.9
- 8 Claude Opus 5 ↓1 69.9
- 9 GPT-5.6 Luna ↓3 69.7
- 10 GLM-5.3 ↑5 69.6
Substitution
24 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 69.0
- 2 Claude Fable 5 ↑3 68.2
- 3
Gemini 3.6 Flash ↑7 68.1
- 4 Claude Opus 5 ↑3 67.2
- 5
Qwen 3.8 Max ↑7 66.6
- 6
DeepSeek V4 Pro 0813 ↑5 66.4
- 7 GPT-5.6 Sol Pro ↓4 66.2
- 8 Grok 4.6 ↓7 66.1
- 9
Qwen3.8-2.4T-A95B ↓1 66.0
- 10
Tencent Hy3 ↑3 66.0
Panel 1
24 models we track have a score here.
- 1
Gemini 3.1 Pro ↑1 64.5
- 2 GPT-5.6 Sol Pro ↑1 64.3
- 3 Claude Fable 5 ↑2 63.5
- 4
Muse Spark 1.2 62.8
- 5 GPT-5.6 Luna ↑1 62.7
- 6 Grok 4.6 ↓5 62.7
- 7
Qwen3.8-2.4T-A95B ↑1 62.4
- 8
Gemini 3.6 Flash ↑2 61.8
- 9 Claude Opus 5 ↓2 61.6
- 10 Claude Sonnet 5 ↑8 61.1
Panel 2
24 models we track have a score here.
- 1 Grok 4.6 67.5
- 2
Gemini 3.1 Pro 65.5
- 3
Muse Spark 1.2 ↑1 64.7
- 4 GPT-5.6 Sol Pro ↓1 64.1
- 5
DeepSeek V4 Pro 0813 ↑6 64.1
- 6 Claude Opus 5 ↑1 63.4
- 7 Kimi K3 ↑2 63.4
- 8
MiniMax-M3 ↑6 63.3
- 9 Claude Fable 5 ↓4 63.2
- 10
Qwen 3.8 Max ↑2 62.6
2 models have held number one on the official leaderboard since its release in August 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official FlavourBench Complete Core leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official FlavourBench Complete Core leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
Versions
More in Writing and taste
- Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
- WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
- Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing.
MiniMax-Text-01 81.3%
- DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate.
DeepSeek-V4-Pro 62.6%
- Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
- Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right.
Muse Spark 0.21
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (27 entries).
- Pass Models scored 24 models we track, plus 3 other entries on its leaderboard.
- Pass Newest score The newest is from August 2026, for GLM-5.3.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 24 rows for models we track and 3 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.