Live19 models · 2 open source · avg 38.2
U

Unknown

Top Model
PaLM 2-L
avg score
19
Total Models
tracked on BenchGecko
2
Open Source
11% of models
Cheapest Model
No pricing data
38.2
Avg Benchmark
across 19 scored models

Model Categories

LLM19

Open Source Ratio

11%
2 open source17 proprietary
#ModelAvgaider editaider poly?ANLI?APEX-Agents?ARC AI2?ARC-AGI?ARC-AGI-2?aa agentic?aa coding ?aa qualityseal audioseal audioseal audioBalrog?BBH?hf bbhC-EvalCadEval?charxiv re?charxiv re?arena elo arena elo chess puzz?CMMLUCSQA2Cybench?deepresear?EnigmaEvalfiction li?Fortressfrontierma?frontierma?frontiermafrontiermaGeoBench?GPQAGPQA diamond?graphwalks?GSM8K?GSO-Bench?HellaSwag?HELM · GPQAhelm ifevahelm mmlu helm omni helm wildbHLE?hle toolsseal humanseal humanIFEvaljp jcommonJHumanEvalJMMLUJNLIJSQuADLAMBADA?lech mazur?livebench livebench livebench livebench livebench livebench livebench livebench jp overallMASKMATH level 5?MATH Level 5MCP AtlasMMLU?MMLU-PROMMMLUmmmlu armmmlu bnmmmlu zhmmmlu frmmmlu demmmlu himmmlu idmmmlu itmmmlu jammmlu kommmlu ptmmmlu esmmmlu swmmmlu yoseal multiMultiNRCMUSROpenBookQA?oc aime202oc gpqa dioc hleoc ifevaloc livecodoc mmlu prOSWorld?otis mock ?PIQA?posttrainbseal pro rseal pro rseal propeseal remotScienceQA?SciPredictSimpleBench?simpleqa v?seal swe aseal swe aswe bench swe bench swe bench seal swe bseal swe bswe bench ?swe bench ?terminal b?the agent ?TriviaQA?TutorBenchUSAMOVideoMME?VISTAseal visuaVPCT?WeirdML?Winogrande?$/1M inContextReleased
1
U
PaLM 2-L Unknown
81.8----58.9-----------------------------------82.4--------------------------------------------------------------------------------86.1-------66.0N/A-Jan 242y ago
2
U
Muse Spark Unknown
74.6-------28.758.643.1-----------1487.0--------39.014.6----86.4---------37.6----------------------------------------------------88.9---------66.3--------------------N/A-Jan 242y ago
3
U
PaLM 2-M Unknown
68.1----53.2-----------------------------------78.7--------------------------------------------------43.2-----------------------------81.7-------58.4N/A-Jan 242y ago
4
U
PaLM 2-S Unknown
61.7----46.1-----------------------------------76.0--------------------------------------------------41.6-----------------------------75.2-------55.8N/A-Jan 242y ago
5
U
internlm-20b Unknown
60.4----75.6---------36.7-----------------------62.9-70.8---------------71.8--------------34.7----------------------------60.6-----------------------------N/A-Jan 242y ago
6
U
Stable Beluga 2 Unknown
60.3----81.5---------59.141.3-------------------8.8--69.6-78.8---------37.9-----71.3------------4.4-58.125.9-----------------18.6---------66.6-----------------------------N/A-Jan 242y ago
7
U
Nemotron-4 15B Unknown
59.0----40.7---------44.9-----------------------46.0-76.5------------------------------44.9----------------------------64.8----------------------------56.0N/A-Jan 242y ago
8
U
Yi 6B UnknownOpen
43.8----33.7---------29.635.5-------------------15.6--44.9-65.9---------30.5-----------------5.25.1-52.037.9-----------------9.7--------------------------------------42.6N/A-Jan 242y ago
9
U
Baichuan 2-7B Unknown
39.2----10.0---------22.1-----------------------24.6-57.3---------------73.3--------------38.9----------------------------56.2-----------------------------N/A-Jan 242y ago
10
U
MPT-30B Unknown
32.2----34.1---------17.36.5-------------------1.3--34.4-68.5---------21.5-----70.0------------1.6-30.52.3-----------------2.936.0--------63.8--------------------73.6-------42.0N/A-Jan 242y ago
11
U
XGen-7B Unknown
32.2----21.6-----------------------------------65.6------------------------------15.1-------------------20.3--------51.0----------------------------29.8N/A-Jan 242y ago
12
U
StarCoder 2 15B UnknownOpen
30.9----29.6----------20.4-------------------3.1--57.7-----------27.8------------------6.0-52.115.0-----------------2.9--------------------------------------28.6N/A-Jan 242y ago
13
U
vicuna-13b-v1.1 Unknown
30.2----24.3---------24.1-----------------------28.1-43.7--------------------------------------------------10.7--------54.8----------------------------41.6N/A-Jan 242y ago
14
U
Dolly 2.0-12b Unknown
26.3----19.5-----------------------------------61.1------------------------------1.6-------------------18.9--------50.8----------------------------23.6N/A-Jan 242y ago
15
U
Baichuan1-7B Unknown
21.2--------------10.0-----------------------9.2--------------------------------23.1----------------------------52.4-----------------------------N/A-Jan 242y ago
16
U
INTELLECT-1 Unknown
21.2----39.4---------13.11.0-------------------0.0--38.6-61.9---------17.6------------------0.0-33.21.3-----------------4.1--------------------------------------31.6N/A-Jan 242y ago
17
U
RedPajama-INCITE-7B-Base Unknown
17.7----18.8----------5.1-------------------0.7----60.4---------20.8------------------1.6-1.72.2-----------------3.020.0--------53.8----------------------------27.6N/A-Jan 242y ago
18
U
Magistral Small 1.1 Unknown
16.7-----5.00.0-----------------------------31.2--------------------------------------------------------------29.9------------------------------N/A-Jan 242y ago
19
U
stablelm-tuned-alpha-7b Unknown
0.5----2.7----------------952.0------------------20.9--------------------------------------------------9.9--------31.6----------------------------3.0N/A-Jan 242y ago
90+ Gold 80-89 70-79 60-69 <60Scores in % unless noted. Avg = unweighted mean across tested benchmarks.

Quick answers · sourced from our data

How many models does Unknown have?

BenchGecko tracks 19 models from Unknown, of which 2 (11%) are open source. Every entry is updated daily from live provider feeds.

What is the best model from Unknown?

PaLM 2-L is currently the highest scoring Unknown model we track, with an average benchmark score of 73.4. Scores are computed across every public benchmark we have data for.

How does Unknown compare on benchmarks?

Unknown models average 38.2 across the benchmarks we track · see the All Providers page for the full ranking by model count, open source ratio, and average score.

Is Unknown open source?

2 of 19 Unknown models are open source (11%). The rest are proprietary · closed weights served via API.