# Excel Modeling Benchmark v1.1 (EMB v1.1)

> Excel financial modeling from a template or from scratch, with updated grading in v1.1.

Canonical page: https://benchlm.ai/benchmarks/emb-v1-1

- Category: [Agentic](/agentic)
- Last updated: October 27, 2026

Evaluation results published by [Vals AI](https://www.vals.ai/benchmarks/emb-v1-1). Published leaderboard aggregates and evaluation settings only. Dataset contents are not included.

## About EMB v1.1

- Year: 2026
- Tasks: Excel-based financial modeling tasks
- Format: Equally weighted mean of seven category scores
- Difficulty: Professional finance modeling
- Paper: [Excel Modeling Benchmark v1.1](https://www.vals.ai/benchmarks/emb-v1-1)

Version 1.1 switches the Scratch judge to GPT-6 Luna and fixes Template sheet-name matching. Accuracy averages tasks within seven categories, then weights the categories equally. Scores are not directly comparable with v1.0. Partial credit can include incomplete work; the table stays display only.

EMB v1.1 is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (35 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Claude Fable 5.1](/models/claude-fable-5-1) | — | Anthropic | 76.73% |
| 2 | [Gemini 4 Carbon](/models/gemini-4-carbon) | high reasoning | Google | 76.47% |
| 3 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | — | Anthropic | 75.90% |
| 4 | [Claude Opus 5.5](/models/claude-opus-5-5) | — | Anthropic | 75.84% |
| 5 | [Muse Wonder Full](/models/muse-wonder-full) | max reasoning | Meta | 75.00% |
| 6 | [Gemini 4 Argon](/models/gemini-4-argon) | high reasoning | Google | 74.83% |
| 7 | [GPT-6.1 Terra](/models/gpt-6-1-terra) | max reasoning | OpenAI | 73.33% |
| 8 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | high reasoning | Google | 72.87% |
| 9 | [GPT-6 Astra](/models/gpt-6-astra) | max reasoning | OpenAI | 72.68% |
| 10 | [Muse Wonder](/models/muse-wonder) | max reasoning | Meta | 72.50% |
| 11 | [Qwen3.8 Max Internal](https://www.vals.ai/models/alibaba_qwen3.8-max-internal) | — | Alibaba | 71.98% |
| 12 | [Grok 4.7](/models/grok-4-7) | xhigh reasoning | xAI | 71.50% |
| 13 | [Kimi K3](/models/kimi-k3) | max reasoning | Moonshot AI | 71.26% |
| 14 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | max reasoning | OpenAI | 71.09% |
| 15 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | max reasoning | Moonshot AI | 70.00% |
| 16 | [GPT-6 Luna](/models/gpt-6-luna) | max reasoning | OpenAI | 69.95% |
| 17 | [Step 5 Preview](/models/step-5-preview) | — | StepFun | 69.55% |
| 18 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | max reasoning | DeepSeek | 69.17% |
| 19 | [GLM-5.3](/models/glm-5-3) | max reasoning | Z.AI | 69.11% |
| 20 | [Mistral Large 4](/models/mistral-large-4) | high reasoning | Mistral | 68.97% |
| 21 | [Hy4 preview](/models/hy4-preview) | — | Tencent | 68.95% |
| 22 | [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | — | Xiaomi | 68.88% |
| 23 | [MiniMax M3.1 Flash](/models/minimax-m3-1-flash) | — | MiniMax | 67.84% |
| 24 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | max reasoning | DeepSeek | 67.76% |
| 25 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | — | Xiaomi | 67.35% |
| 26 | [GLM-5.3-Flash](/models/glm-5-3-flash) | max reasoning | Z.AI | 66.25% |
| 27 | [Qwen3.8 Max](/models/qwen3-8-max) | — | Alibaba | 65.99% |
| 28 | [Claude Haiku 5.5](/models/claude-haiku-5-5) | — | Anthropic | 65.48% |
| 29 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 65.13% |
| 30 | [Beam 1.0](https://www.vals.ai/models/reflection_Beam-1.0) | — | Reflection | 64.73% |
| 31 | [Muse Spark Open](/models/muse-spark-open) | xhigh reasoning | Meta | 61.98% |
| 32 | [MiniMax M3](/models/minimax-m3) | — | MiniMax | 59.75% |
| 33 | [Mercury 3](/models/mercury-3) | high reasoning | Inception | 57.88% |
| 34 | [Inkling](/models/inkling) | 0.99 reasoning | Thinking Machines Lab | 40.97% |
| 35 | [Inkling-Small](/models/inkling-small) | 0.99 reasoning | Thinking Machines Lab | 40.82% |

## FAQ

### What does EMB v1.1 measure?

Excel financial modeling from a template or from scratch, with updated grading in v1.1.

### Which model leads the published EMB v1.1 snapshot?

Claude Fable 5.1 currently leads the published EMB v1.1 snapshot with a score of 76.73%.

### How many models are evaluated on EMB v1.1?

The October 27, 2026 contains 35 AI models.

### Does EMB v1.1 affect BenchLM's overall score?

Not directly. EMB v1.1 is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.