TML-d24-varloop-research
TML-d24-varloop-research is behind the leaders in multimodal tasks and coding. Too few results yet to rate reasoning, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
Capability profile
Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.
Too few results yet to rate Reasoning, Agentic, Safety, Long Context, Math, Multilingual, Instruction Following or Factuality.
Price
No current price is tracked for this model. See the rate card
Evidence
11results on11benchmarks
- 11 vendor-reported
From 1 source · latest Nov 21, 2026 · How verification works
TML-d24-varloop-research benchmark results
11 results on 11 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.
30.9% behind the leader1 of 6 ranked benchmarks measured
- MMMU-Pro73.20Nov 21, 2026MMMU Pro (Standard 10)
35.2% behind the leader2 of 10 ranked benchmarks measured
- 79.60Nov 21, 2026
- 72.00Nov 21, 2026
More results
Benchmarks outside the capability baskets. They are not ranked against a leader.
- BabyVision original49.20Nov 21, 2026BabyVision (original)
- OmniDocBench v1.692.50Nov 21, 2026
- GDP (Surge AI)20.00Nov 21, 2026GDP.pdf
- EnterpriseOps-Gym (LangChain ReAct loop)37.60Nov 21, 2026
- 63.30Nov 21, 2026
- BrowseComp (original, no context management)71.00Nov 21, 2026
Show 2 more resultsHide 2 results
- DeepSWE 1.148.20Nov 21, 2026DeepSWE v1.1
- SWEBench Pro v2 (Hard)78.40Nov 21, 2026
TML-d24-varloop-research: common questions
Who makes TML-d24-varloop-research?
TML-d24-varloop-research is made by Thinking Machines.
When was TML-d24-varloop-research released?
TML-d24-varloop-research's weights were first published on Hugging Face on Nov 18, 2026.
What is TML-d24-varloop-research good at?
TML-d24-varloop-research is behind the leaders in multimodal tasks and coding. Too few results yet to rate reasoning, agentic tasks, safety, long context, math, multilingual tasks, instruction following, or factuality.
How many benchmarks has TML-d24-varloop-research been tested on?
We track 11 results for TML-d24-varloop-research on 11 benchmarks from 1 source. The latest was recorded on Nov 21, 2026.
About this record
Where TML-d24-varloop-research's numbers come from, and every name it appears under.
- Tracked since
- Nov 20, 2026
- Newest source mention
- Nov 20, 2026
Where the results come from
Verification: 11 scores · 0 independently verified · 11 vendor-reported. How these tiers are assigned
From 1 source on 1 site. Hugging Face supplies all of them. Bars are coloured by trust tier.
- huggingface.co11