whatmodel.sh / Amazon Nova Experimental Chat (12-10)

Amazon Nova Experimental Chat (12-10)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Amazon Nova Experimental Chat (12-10) is a closed-weights language model from Amazon. Licence: proprietary.

Catalogue identity notes

Exact Arena entry 'amazon-nova-experimental-chat-12-10' in the October 2026 pinned dataset. Comparison identity; no public run route inferred from leaderboard inclusion.

64.3±3.3comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of Amazon Nova Experimental Chat (12-10), out of 1132 with a score, then more from Amazon.

#modelscorewhereRAMreleased
204Mistral Medium 3.5 (128B) Mistral65±1api $3.00/M +local~42GB2026-04
205Command A+ (05-2026) Cohere64±1api price unknown +local~71GB2026-05
206Amazon Nova Experimental Chat (12-10) Amazon64±3comparison only
207Claude Haiku 4.5 Anthropic64±1api $2.00/M2025-10
208Nemotron-Labs-3 Puzzle 75B-A9B NVIDIA64±1local~35GB2026-06
more from Amazon
134Amazon Nova Experimental Chat (26-02-10) Amazon68±3comparison only
162Amazon Nova Experimental Chat (26-01-10) Amazon67±3comparison only
167Nova 2 Omni (Preview) Amazon66±7api $0.93/M2025-11

see all LLMs · find the ones that fit your machine

$ what it's good at

chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #153 of 579 * · 95% of its score · 1 test

Beats LongCat 2.0 (1.6T-A48B), GPT-5 mini, Qwen3.5 35B-A3B here, though they rank higher overall. Trails LFM2.5 2.6B, Nemotron-Cascade-8B, DeepSeek V3 0324 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
LMArena (text)1393.9 ✎▁▁▁▂▃▃▃▆▆▇█▃ beats 237/379avg 1268▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%blunt

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · LMArena leaderboard dataset 95%

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

sourceresultsshare of the scorelicence
LMArena leaderboard dataset1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%CC BY 4.0
prior · pull toward the middle▇ 5%
weighted average= 64.3

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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