By field of work
Choosing an LLM for business and finance
Ranked by human ratings on questions classified as business and finance work.
- Highest rated
- △Gemini 4 Argon $4
- On a budget
- Muse Spark 1.2 Meta AI $2
- Rating gap 7
- Within the margin of error, so about the same
About the same rating as the cheaper Muse Spark 1.2 ($2); the gap is within the margin of error, so Muse Spark 1.2 is enough.
Rating and price
The closer to the top left, the cheaper and better rated the model.
OpenAIZ.aiGoogleMistralMetaXiaomiStepFunAlibabaAnthropicCohereMiniMaxxAIDeepSeekMoonshotNVIDIAMicrosoftOther
Best-rated model at each price
First line: model / Human rating, second line: price estimate
| Model | Developer | Human rating | Price |
|---|---|---|---|
| △Gemini 4 Argon | $4 (in $2, out $10) | ||
| Muse Spark 1.2 | Meta | $2 (in $1.25, out $4.25) | |
| △Gemini 3.7 Flash | $1.5 (in $0.75, out $3.75) | ||
| MiMo-V2.5 Pro | Xiaomi | $0.54 (in $0.435, out $0.87) | |
| △GLM-5.3 Flash | Z.ai | $0.24 (in $0.15, out $0.5) | |
| MiMo-V2.6 Flash | Xiaomi | $0.18 (in $0.14, out $0.28) | |
| Step 3.5 Flash | StepFun | $0.16 (in $0.1046, out $0.3138) | |
| △Mistral Small 3.2 | Mistral | $0.15 (in $0.1, out $0.3) | |
| GPT-5 nano | OpenAI | $0.14 (in $0.05, out $0.4) |
All models (highest human rating first)
Second line: price (input / output) / context / released / supports Tools Image JSON □ Compare
| Pick | Compare | Model | Developer | Human rating | Overall (human rating) | Input $ /1M | Output $ /1M | Context | Supports | Weights | Released | Price and specs |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 1517 | $2 | $10 | 1.05M | $2 / $10 1.05M 2026-09 | |||||||
| Claude Opus 4.7 | Anthropic | 1501 | $5 | $25 | 1M | $5 / $25 1M 2026-04 | ||||||
| Muse Spark 1.2 | Meta | 1491 | $1.25 | $4.25 | 1.05M | $1.25 / $4.25 1.05M 2026-08 | ||||||
| Muse Spark 1.3 | Meta | 1496 | $1.25 | $4.25 | 1.05M | $1.25 / $4.25 1.05M 2026-09 | ||||||
| Claude Fable 5 | Anthropic | 1503 | $10 | $50 | 1M | $10 / $50 1M 2026-06 | ||||||
| Claude Opus 4.6 | Anthropic | 1503 | $5 | $25 | 1M | $5 / $25 1M 2026-02 | ||||||
| Muse Wonder | Meta | 1509 | $4 | $20 | 1.05M | $4 / $20 1.05M 2026-10 | ||||||
| Claude Opus 5.5 | Anthropic | 1509 | $4 | $20 | 1M | $4 / $20 1M 2026-09 | ||||||
| Muse Spark 1.1 | Meta | 1490 | $1.25 | $4.25 | 1M | $1.25 / $4.25 1M 2026-07 | ||||||
| GPT-5.5 | OpenAI | 1482 | $5 | $30 | 1.05M | $5 / $30 1.05M 2026-04 | ||||||
| Muse Spark | Meta | 1489 | — | — | — | 2026-04 | ||||||
| Claude Opus 4.8 | Anthropic | 1482 | $5 | $25 | 1M | $5 / $25 1M 2026-05 | ||||||
| Kimi K3 | Moonshot | 1487 | $3 | $15 | 1.05M | $3 / $15 1.05M 2026-07 | ||||||
| GPT-5.6 Sol | OpenAI | 1485 | $4 | $20 | 1.05M | $4 / $20 1.05M 2026-07 | ||||||
| Claude Opus 5 | Anthropic | 1491 | $5 | $25 | 1M | $5 / $25 1M 2026-07 | ||||||
| GPT-6.1 Sol | OpenAI | 1480 | $2 | $10 | 1.05M | $2 / $10 1.05M 2026-09 | ||||||
| Qwen3.8 Max | Alibaba | 1483 | $2 | $6 | 1M | $2 / $6 1M 2026-08 | ||||||
| Claude Fable 5.1 | Anthropic | 1503 | $10 | $50 | 1M | $10 / $50 1M 2026-09 | ||||||
| GPT-5.2 Chat | OpenAI | 1476 | — | — | 128K | 128K 2026-02 | ||||||
| Gemini 3.7 Flash | 1490 | $0.75 | $3.75 | 1.05M | $0.75 / $3.75 1.05M 2026-08 | |||||||
| Claude Sonnet 4.6 | Anthropic | 1472 | $3 | $15 | 1M | $3 / $15 1M 2026-02 | ||||||
| GPT-5.4 | OpenAI | 1475 | $2.5 | $15 | 1.05M | $2.5 / $15 1.05M 2026-03 | ||||||
| Gemini 3.8 Flash | 1496 | $0.75 | $3.75 | 1.05M | $0.75 / $3.75 1.05M 2026-09 | |||||||
| Gemini 3.1 Pro (preview) | 1487 | $2 | $12 | 1.05M | $2 / $12 1.05M 2026-02 | |||||||
| DeepSeek-V4.1 Flash | DeepSeek | 1476 | — | — | 1M | 1M 2026-09 | ||||||
| Claude Sonnet 5.5 | Anthropic | 1478 | $2 | $10 | 1M | $2 / $10 1M 2026-09 | ||||||
| GPT-5.5 Instant | OpenAI | 1473 | — | — | — | 2026-05 | ||||||
| ERNIE 5.1 | Baidu | 1467 | — | — | 119K | — | 119K | |||||
| Gemini 3 Pro | 1486 | — | — | 1.05M | 1.05M 2025-11 | |||||||
| GLM-5.3 | Z.ai | 1481 | $1.4 | $4.4 | 1M | $1.4 / $4.4 1M 2026-08 | ||||||
| GPT-6 Astra | OpenAI | 1477 | $10 | $50 | 1.05M | $10 / $50 1.05M 2026-09 | ||||||
| Gemini 3.6 Flash | 1483 | $0.75 | $3.75 | 1.05M | $0.75 / $3.75 1.05M 2026-07 | |||||||
| Claude Opus 4.5 | Anthropic | 1474 | $5 | $25 | 200K | $5 / $25 200K 2025-11 | ||||||
| MiMo-V2.5 Pro | Xiaomi | 1467 | $0.435 | $0.87 | 1.05M | $0.435 / $0.87 1.05M 2026-04 | ||||||
| GLM-5.3 Flash | Z.ai | 1476 | $0.15 | $0.5 | 1M | $0.15 / $0.5 1M 2026-08 | ||||||
| Grok 4.20 (beta1) | xAI | 1475 | — | — | — | — | ||||||
| Gemini 3 Flash | 1473 | — | — | 1.05M | 1.05M 2025-12 | |||||||
| Gemini 3.5 Flash | 1477 | $1.5 | $9 | 1.05M | $1.5 / $9 1.05M 2026-05 | |||||||
| DeepSeek-V4 Pro (2026-08) | DeepSeek | 1465 | $0.66 | $1.98 | 1M | $0.66 / $1.98 1M 2026-08 | ||||||
| GPT-5.6 Terra | OpenAI | 1467 | $2 | $12 | 1.05M | $2 / $12 1.05M 2026-07 |
How to read this page
- Also shown (not used for ranking): human ratings on all questions. 385 models have ratings.
- Bars are drawn from 800 to 1550.
- The human rating comes from people giving two models the same question and picking the better answer. With a gap of 50, the higher-rated model is picked about 57% of the time; 64% at 100 and 76% at 200 (a gap of 0 is even odds). Differences where the ± ranges overlap are within the margin of error, so about the same.
- Only models rated higher than every cheaper model are listed, best first. For about the same rating, pick the cheapest row in this table. The top row without △ within the price you can pay is the pick. A △ row costs more than the row below it without △, yet its rating is about the same (the gap is within the margin of error).
- “On a budget” is the highest-rated model at $2 or less per million tokens (or at your price cap, when that is lower).
- △ marks rows whose rating gap is within the margin of error (about the same). A row without △ is rated higher than the nearest row below it without △, by more than the margin of error.
- Best at each price
- Prices are what developers pay to use a model through its API, separate from app subscriptions. The unit is one million tokens. A token is a small piece of text (about three quarters of an English word); one million tokens is roughly 8 to 10 novels. Reading (input) and writing (output) are priced differently; here they are blended 3 : 1. For example, at $4, one everyday question and answer (about 1,000 tokens) costs about 0.4 cents. Models without a known price are left out.
- In the Supports column the icons are, from left: can use tools / can read images / can answer in a fixed format (JSON); faded means not supported or unknown.
- Open-weights models have their contents (the weights) published, so you can also run them on your own computer or server. Models without the open-weights mark are normally used through the developer's own services (apps or API); for some models the weights status is unknown.
- Names such as ChatGPT next to a model are the consumer services its developer offers. Check on the service itself whether that model is available there.
- Vertical is Human rating, horizontal is price (the horizontal scale gets coarser to the right). Points joined by the step line are the best-rated models at each price. Hover or tap a dot to see the model's name.
Data: Arena, Epoch AI, Swallow LLM team (CC BY 4.0), Models.dev (MIT), updated 2026-10-24, data sources