Bespoke Labs
Release: 2026-10-16
Tested on: 2026-10-16 00:55
bespokelabs/bespoke-nimble-9b-v3::none
9BDenseWeights available Summary
Nimble v3 9B scores 0.8 on AI BENCHY and ranks #430. It has 10.0 reliability, a 4.4% pass rate, ~$0.001 total cost, and 363ms average response time.
What makes Nimble v3 9B unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-10-16
- Parameters
- 9B
- Architecture
- Dense
- Availability
- Weights available
- License
- CC-BY-NC-4.0
Bespoke Labs LoRA adapter merged into Qwen3.5-9B text weights by Ollama. Local Q8_0 GGUF checkpoint with Q4_0 KV cache; native probability-based decisions, without free-form generation or reasoning effort controls. The adapter is noncommercial under CC BY-NC 4.0; the base is separately Apache-2.0. The 9B count is the published rounded model size.
0.8
Consistency
3.0
10.0
~$0.001
Total Output Tokens
0
Total Input Tokens
103,770
Estimated benchmark electricity cost
~$0.001
Wrong Tests: 6
Attempt pass rate: 4.4%
Benchmark coverage: 21/69 attempts. Choices supplied by adapters. Supports 7/23 tests. Other tests are unsupported, not failed. Score uses the full suite.
Flaky tests
0
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Nimble v3 9BdefaultvsTev1 4B ExperimentaldefaultNimble v3 9BdefaultvsSolar DecidedefaultNimble v3 9BdefaultvsMicrosoft-Decision-1defaultNimble v3 9BdefaultvsSolar Decide FlashdefaultNimble v3 9BdefaultvsGemini 3 Flash PreviewhighNimble v3 9BdefaultvsD1defaultNimble v3 9BdefaultvsClef OmnidefaultNimble v3 9BdefaultvsClassify-1defaultNimble v3 9BdefaultvsJev 1.14defaultNimble v3 9BdefaultvsKev 4Bdefault
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 2.5 | 2.5 | |
| Coding | 0.0 | 0.0 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 3.0 | 10.0 | |
| Domain specific | 2.0 | 6.7 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 1.5 | 5.0 | |
| Puzzle Solving | 1.7 | 3.3 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |