utCOMPARE MODELS
Smarter, faster, cheaper.
On one chart.
See how models rate on intelligence, coding and math, how fast they answer, and what they cost. Filter to open-weight models of a size you can run, and highlight the ones you care about.
No scores yet for LFM2.5-Encoder-350M-Spellchecker. The chart covers text models rated on LMArena’s leaderboard; image, video and audio models aren’t rated here.
- Open weights
- API only
- License not stated
- Highlighted
Overall rating higher is better · gaps smaller than the ± margin are effectively ties
Overall rating vs speed up and to the right is better and faster
Scout’s model lab has timed 1 of these models on its RTX 3060 so far. More are added as the lab tests new downloads each night.
| Model | Intelligence | Coding | Math | Votes | Cloud speed | First token | RTX 3060 | Price in / out per 1M | Size | Access |
|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon (High)google | 1,524 | 1,559 | 1,529 | 4.9K | — | — | — | $2 / $10 | — | API only |
| Muse Wonder (Max)meta | 1,509 | 1,548 | — | 3.2K | — | — | — | $4 / $20 | — | API only |
| Claude Opus 5.5 (High)anthropic | 1,508 | 1,548 | 1,502 | 8.3K | — | — | — | $4 / $20 | — | API only |
| Claude Fable 5 (High)anthropic | 1,504 | 1,551 | 1,523 | 42K | — | — | — | $10 / $50 | — | API only |
| Claude Opus 4.6 (High)anthropic | 1,503 | 1,548 | 1,518 | 81.4K | — | — | — | $5 / $25 | — | API only |
| Claude Fable 5.1 (Max)anthropic | 1,502 | 1,537 | 1,525 | 14.6K | — | — | — | $10 / $50 | — | API only |
| Claude Opus 4.7 (High)anthropic | 1,501 | 1,551 | 1,504 | 65.1K | — | — | — | $5 / $25 | — | API only |
| Claude Opus 4.6anthropic | 1,497 | 1,547 | 1,505 | 86.1K | — | — | — | $5 / $25 | — | API only |
| Gemini 3.8 Flash (High)google | 1,496 | 1,528 | 1,522 | 37.5K | — | — | — | $0.75 / $3.75 | — | API only |
| Muse Spark 1.3 (Max)meta | 1,494 | 1,535 | 1,504 | 17.6K | — | — | — | $1.25 / $4.25 | — | API only |
| Claude Opus 4.7anthropic | 1,494 | 1,546 | 1,491 | 66.2K | — | — | — | $5 / $25 | — | API only |
| Muse Spark 1.2 (xHigh)meta | 1,493 | 1,539 | 1,484 | 8.2K | — | — | — | $1.25 / $4.25 | — | API only |
| Muse Spark 1.1meta | 1,490 | 1,533 | 1,496 | 42.8K | — | — | — | $1.25 / $4.25 | — | API only |
| Claude Opus 5 (Max)anthropic | 1,490 | 1,529 | 1,514 | 32.5K | — | — | — | $5 / $25 | — | API only |
| Claude Opus 5 (High)anthropic | 1,490 | 1,533 | 1,522 | 66.8K | — | — | — | $5 / $25 | — | API only |
| Muse Sparkmeta | 1,489 | 1,529 | 1,467 | 14.2K | — | — | — | — | — | API only |
| Gemini 3.7 Flash (High)google | 1,488 | 1,518 | 1,506 | 27.2K | — | — | — | $0.75 / $3.75 | — | API only |
| Kimi K3 (Max)moonshot | 1,487 | 1,538 | 1,501 | 32.8K | — | — | — | — | 2.8T | Open weightsKimi K3 license |
| Gemini 3.1 Pro Previewgoogle | 1,487 | 1,521 | 1,488 | 127.6K | — | — | — | $2 / $12 | — | API only |
| Gemini 3 Progoogle | 1,486 | 1,517 | 1,477 | 42.1K | — | — | — | — | — | API only |
Ratings: LMArena text leaderboard ↗ (Oct 15, 2026), with style control, from the public dataset under CC BY 4.0. Ratings come from people comparing two anonymous answers and picking the better one; Intelligence is the overall rating, Coding and Math are LMArena’s categories. Speed is measured by Scout: cloud speed is the median of daily timed runs through OpenRouter, and RTX 3060 speed comes from Scout’s own model lab. Prices are listed API rates from Models.dev. How Scout builds this chart