Loading comparison…
HEAD TO HEAD
Hanno Labs: bosun and Contrastive-LM: clm, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | hanno-labs/bosun | contrastive-lm/clm |
|---|---|---|
| Summary | Hanno Labs' small calibrated decision model. A LoRA on Qwen3-1.7B plus trained decision-token embeddings with stable slots, returning the full distribution over up to 255 caller-defined choices and a null slot for Choice, Score and Noul questions. | Contrastive Language Models score a state against a set of candidate actions with a contrastive objective. Two projection heads on frozen Qwen3-8B embeddings, trained with InfoNCE; clm-serve maps Choice, Score and Noul onto candidate ranking. |
| Decides | choice, score, noul, classify, route | choice, score, noul, rank, classify, route |
| Architecture | bosun | clm |
| Fine-tuned from | qwen/qwen3-1.7b | qwen/qwen3-8b |
| License | apache-2.0 | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | 84.9% | — |
| Calibration error | 0.050 | — |
| Valid action rate | — | — |
| Median latency | — | — |
| p95 latency | — | — |
| Evaluation suite | DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families) | — |
| Latest version | 3.1.0 | 2026.09.25 |
| Variants | LICENSE, NOTICE, adapter, tokenizer | LICENSE |
| Size of latest version | 83.9 MB | 72.1 MB |
| Files | 17 | 3 |
| Downloads | 0 | 5 |
| Stars | 0 | 0 |
| Tags | system-one, qwen, lora, calibrated, gguf, 2b | system-one, contrastive, qwen, ranking, 8b |
| Updated | Sep 30, 2026 | Sep 30, 2026 |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
bosun is from Hanno Labs and clm from Contrastive-LM. Both have open weights you can download and run. Both answer choice, score, noul, classify and route questions. Only clm answers rank. bosun is the smaller model, at 2.0B parameters to 8.0B.
Only bosun publishes an accuracy figure (84.9% on DecisionBench (Hanno-Labs/decision-bench, 23,900 rows; seen task families)); clm does not, so there is no comparison to make without your own test.
bosun: Free (open weights). clm: Free (open weights). Open weights cost nothing per call beyond your own hardware.
Yes, both: systemone pull hanno-labs/bosun and systemone pull contrastive-lm/clm download the weights.