whatmodel.sh / Nova Micro
Nova Micro
↗ share
+ contribute
Nova Micro is a closed-weights language model from Amazon, released December 2024.
$ how it compares
The LLMs ranked either side of Nova Micro, out of 828 with a score, then more from Amazon.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 501 |  Command R (08-2024) | 46±1 | api $0.26/M +local | ||
| 502 |  GPT-3.5 Turbo (0301) | 46±1 | comparison only | ||
| 503 | Nova Micro | 46±2 | api $0.061/M | ||
| 504 |  T5 Base | 46±9 | local | ||
| 505 |  OpenChat 3.5 0106 | 46±1 | local | ||
| more from Amazon | |||||
| 184 | Nova 2 Pro (Preview) | 64±2 | api $3.78/M | ||
| 269 | Nova 2 Lite | 58±2 | api $0.94/M | ||
| 339 | Nova Premier | 54±2 | api $5.00/M | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #252 of 300 · 56% of its score · 4 tests
Beats DeepSeek R1 0528 Qwen3 8B, Magistral Small 1.0 (2506), Llama 4 Scout (109B-A17B) here, though they rank higher overall. Trails Granite 4.0 H 1B, Granite 4.0 1B, SmolLM3 3B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MASSIVE-Agents AST (10k, zero-shot) lab | 5.5% ✎ | █····███·███ beats 2/6 | 24% |
| BFCL V4 (December 2025 archive) | 22.3% ✎ | ▁▁▁▂██▅▅▆▂▂▂ beats 10/77 | 15% |
| BFCL v3 | 51.8% ✎ | ▁▁▁▁▁▃▅█▅▄▁▁ beats 43/114 | 8.7% |
| Galileo Agent Leaderboard v1 (tool selection quality) | 82.9% ✎ | ▃▃▃▃▆▅▆▅█▂▅▂ beats 12/31 | 8.4% |
chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #280 of 393 * · 39% of its score · 1 test
Beats Ministral 3 14B Reasoning 2512, Gemma 4 E4B, Ministral 3 8B here, though they rank higher overall. Trails Flan-T5 XXL, LFM2 700M, EXAONE 3.5 2.4B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1240.7 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 90/379 | 39% |
other tests2 not in a task · 2.8% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 98.4% ✎ | ▁▁▂▃▄▄█▆▃▃▂▁ beats 129/140 | 2.8% |
| Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate) | 94.5% ✎ | ▁▂▁▂▅█▂▃▄▃▁▁ beats 83/98 | 0.0% |
$ where to run it
Through an API
api · Amazon Bedrock · $0.061/M · $0.035 in / $0.14 out per 1M tokens · 128k context · docs.aws.amazon.com ↗ · price sourceUSD per 1M tokens, Standard tier, geo cross-Region inference and in-Region, US East (N. Virginia). Observed 2026-09-25.
$ how the score was worked out · LMArena leaderboard dataset 39%, MASSIVE-Agents — Kulkarni et… 24%, Berkeley Function Calling Lea… 24% and 2 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 1 | 39% |
 MASSIVE-Agents — Kulkarni et al. (2025) · lab-reported | 1 | 24% |
 Berkeley Function Calling Leaderboard result archive | 2 | 24% |
| Galileo Agent Leaderboard (v1 and v2 results) | 1 | 8% |
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 2 | 3% |
| prior · pull toward the middle | 2% | |
| weighted average | = 45.9 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json