Best model for your job
Best AI model for Excel
For Excel and spreadsheets, GPT-6 Astra scores highest on the current data (85.0), weighting reasoning 40%, math 30%, instruction following 30%. The cheapest model in the top 10 is Gemini 3.8 Flash at $0.75 / $3.75 per million tokens.
Last verified
Weights: Reasoning 40%, Math 30%, Instruction Following 30%. Spreadsheet work needs exact formulas and careful step-by-step logic.
| # | Model | Provider | Fit | Reasoning | Math | Instruction Following | Input $/M | Output $/M |
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | OpenAI | 85.0 | 85.1 | 93.5 | 76.3 | $10 | $50 |
| 2 | GPT-6.1 Sol | OpenAI | 84.0 | 81.9 | 93.7 | 77.0 | $2 | $10 |
| 3 | Claude Opus 5.5 | Anthropic | 83.6 | 80.2 | 91.8 | 80.0 | $4 | $20 |
| 4 | Claude Fable 5.1 | Anthropic | 81.3 | 76.7 | 89.6 | 79.2 | $10 | $50 |
| 5 | Claude Fable 5 | Anthropic | 80.9 | 76.8 | 88.5 | 78.6 | $10 | $50 |
| 6 | Claude Opus 5 | Anthropic | 80.5 | 77.2 | 86.2 | 79.2 | $5 | $25 |
| 7 | GPT-5.6 Sol | OpenAI | 78.9 | 74.8 | 85.6 | 77.7 | $4 | $20 |
| 8 | GPT-6 Sol | OpenAI | 78.1 | 74.0 | 87.2 | 74.5 | $2 | $10 |
| 9 | GPT-5.5 | OpenAI | 76.9 | 72.8 | 81.7 | 77.5 | $5 | $30 |
| 10 | Gemini 3.8 Flash | 73.8 | 76.9 | 65.3 | 78.0 | $0.75 | $3.75 | |
| 11 | Claude Opus 4.8 | Anthropic | 72.6 | 64.7 | 78.4 | 77.4 | $5 | $25 |
| 12 | Gemini 3.7 Flash | 72.2 | 70.0 | 69.6 | 77.7 | $0.75 | $3.75 | |
| 13 | GPT-5.6 Terra | OpenAI | 71.7 | 60.7 | 81.6 | 76.4 | $2 | $12 |
| 14 | Claude Sonnet 5.5 | Anthropic | 71.4 | 54.0 | 87.9 | 78.3 | $2 | $10 |
| 15 | Kimi K3 (open weights) | Moonshot AI | 70.8 | 63.0 | 74.2 | 77.7 | $3 | $15 |
| 16 | Gemini 3.1 Pro Preview | 70.4 | 71.7 | 62.1 | 77.0 | $2 | $12 | |
| 17 | GPT-5.4 | OpenAI | 69.9 | 61.8 | 73.5 | 77.1 | $2.50 | $15 |
| 18 | Grok 4.6 | xAI | 67.3 | 61.4 | 67.0 | 75.4 | $2 | $6 |
| 19 | Qwen3.8 Max | Alibaba (Qwen) | 67.0 | 54.4 | 73.2 | 77.6 | $2 | $6 |
| 20 | Muse Spark 1.3 | Meta | 66.8 | 54.0 | 73.1 | 77.5 | $1.25 | $4.25 |
| 21 | Gemini 3.5 Flash | 66.4 | 62.8 | 60.7 | 77.0 | $1.50 | $9 | |
| 22 | Claude Opus 4.6 | Anthropic | 65.8 | 57.8 | 63.0 | 79.5 | $5 | $25 |
| 23 | GPT-5.6 Luna | OpenAI | 65.0 | 47.6 | 77.7 | 75.6 | $0.20 | $1.20 |
| 24 | Claude Opus 4.7 | Anthropic | 65.0 | 53.8 | 66.7 | 78.4 | $5 | $25 |
| 25 | DeepSeek V4 Pro (open weights) | DeepSeek | 64.9 | 56.5 | 64.8 | 76.1 | $0.66 | $1.98 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Top two head to head: GPT-6 Astra vs GPT-6.1 Sol
Frequently asked questions
What is the best ai model for excel?
For Excel and spreadsheets, GPT-6 Astra scores highest on the current data (85.0), weighting reasoning 40%, math 30%, instruction following 30%. The cheapest model in the top 10 is Gemini 3.8 Flash at $0.75 / $3.75 per million tokens.
How is this shortlist built?
Spreadsheet work needs exact formulas and careful step-by-step logic. Each model's category scores are blended with those weights; only ranked models with results in every needed category are listed.
Other jobs
- Best AI model for coding
- Best AI model for debugging
- Best AI model for building websites
- Best local LLM for coding
- Best AI model for agents
- Best AI model for RAG
- Best AI model for research
- Best AI model for studying
- Best AI model for math
- Best AI model for hard reasoning
- Best AI model for data analysis
- Best AI model for data extraction
- Best AI model for writing
- Best AI model for emails
- Best AI model for copywriting
- Best AI model for creative writing
- Best AI model for translation
- Best AI model for language learning
- Best AI model for customer service
- Best AI model for presentations
- Best AI model for PDFs
- Best AI assistant for everyday use