Best LLMs for Classification (2026)
Last refreshed 2026-11-10. Next refresh: weekly.
LLMs for text classification, routing, and moderation in 2026, shown unranked and sorted by release date, newest first.
How we rank
This page is an unranked list of models tagged for classification, routing, or moderation, sorted by release date, newest first. No benchmark score sets the order.
- Eligibility — Models tagged for the classification decision task (routing, moderation, extraction, or classification benchmarks).
- Display order — An unranked list with no podium. Models are sorted by newest release, then by name. A benchmark score is shown beside each model where one exists, for reference; it does not set the order.
- Variant collapse — We keep one row per model family (`familySlug` + parameter tier). This list is unranked, so the row we keep is the sibling that comes first in the list's own display order (see Display order above); if siblings tie on that order, the newest `release` is kept, then the model name and slug decide. Benchmark scores shown beside a model do not choose which sibling is kept.
- Pricing — Lowest tracked commercial token pricing.
Classification models
Unranked. Newest release first.
| Model | Input $/1M | Output $/1M | |
|---|---|---|---|
| K-EXAONE 2.5 ReasoningTools Benchmark score (not used for order): Release 2026-11-09 | — | — | |
| Reflex Vision Benchmark score (not used for order): Release 2026-11-04 | $0.04 | Free | |
| Sarvam Prism Benchmark score (not used for order): Release 2026-11-03 | — | — | |
| Drex Max Finance Vision Benchmark score (not used for order): Release 2026-11-02 | $0.03 | Free | |
| Drex Max v1.1 Vision Benchmark score (not used for order): Release 2026-10-28 | $0.03 | Free | |
| d1-2B Vision Benchmark score (not used for order): Release 2026-10-27 | — | — | |
| d1-Omni-2B Vision Benchmark score (not used for order): Release 2026-10-27 | — | — | |
| Banyan Sapling Benchmark score (not used for order): Release 2026-10-23 | — | — | |
| SEA-LION Guard v2 31B Benchmark score (not used for order): Release 2026-10-21 | — | — | |
| SEA-LION Guard v2 E2B Benchmark score (not used for order): Release 2026-10-21 | — | — | |
| SEA-LION Guard v2 E4B Benchmark score (not used for order): Release 2026-10-21 | — | — | |
| Mercury 3 ReasoningTools Benchmark score (not used for order): Release 2026-10-19 | $0.10 | $0.35 | |
| LFM2.5-24B-A2B ReasoningTools Benchmark score (not used for order): Release 2026-10-13 | $0.05 | $0.70 | |
| Clef-omni Vision Benchmark score (not used for order): HellaSwag 99.1% | $0.15 | Free | |
| Microsoft-Decision-1 Benchmark score (not used for order): Release 2026-10-09 | $0.04 | Free | |
| Beam ReasoningTools Benchmark score (not used for order): Release 2026-10-05 | $1.00 | $3.00 | |
| Kolibri 1 ReasoningTools Benchmark score (not used for order): MMLU-Pro 80% | — | — | |
| Quyet-1.0-Large Benchmark score (not used for order): Release 2026-10-03 | — | — | |
| Quyet-1.0-Medium Benchmark score (not used for order): Release 2026-10-03 | — | — | |
| Torchcast Decision 12B Restricted Benchmark score (not used for order): Release 2026-10-02 | — | — |