Skip to main content

IQuestLanguage modelOpen weights

IQuest-Q1

IQuest-Q1 has no overall index value yet because there are too few independent benchmark results.

PopularityRank 151 of 342 language models

43out of 100new calculation

based on two data groups, mostly search, range 29 to 58

Summary

IQuest-Q1 targets coding with successive tool-use steps in its post-training. The text-based MoE checkpoint handles 524,288 context tokens. Its model card estimates about 320 billion total parameters and 15 billion active parameters.

IQuest publishes local weights under its custom IQuest-Q1 license and documents SGLang and vLLM serving. Multimodal capability is not documented for this checkpoint.

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 9 published benchmark results

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

DeepSWE v1.1 (Show measurement, test conditions, and source)
Source value
64.6
Metric
DeepSWE v1.1 reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
NL2Repo (Show measurement, test conditions, and source)
Source value
63
Metric
NL2Repo reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
CyberGym (Show measurement, test conditions, and source)
Source value
84.5
Metric
CyberGym reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
TerminalBench 2.1 (Show measurement, test conditions, and source)
Source value
83.2
Metric
TerminalBench 2.1 reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
JobBench (Show measurement, test conditions, and source)
Source value
55.7
Metric
JobBench reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
Agents Last Exam (Show measurement, test conditions, and source)
Source value
29.6
Metric
Agents Last Exam reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
HLE no-tools (Show measurement, test conditions, and source)
Source value
39.2
Metric
HLE no-tools reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
IQuest CLIBench (Show measurement, test conditions, and source)
Source value
53.7
Metric
IQuest CLIBench reported score
Unit
No unit provided
Category
source-specific
Direction
Higher is better
Source type
vendor-reported
Evaluator
Provider model card
Status
active
Retrieved at
2026-10-04
Methodology
Vendor-reported result. Official image-only card, visually inspected. Claude Code/Codex/mini-SWE and task-specific time limits; model card treats IQuest CLIBench as in-house.
Context
Source-specific observation; it is not a shared comparison cohort. The source table does not state a unit or scale for this numeric score.
Source Provider model card
MathBench.ai v1.4 combined score (Show measurement, test conditions, and source)
Source value
29
Metric
combined score /100; 0.5 point per problem
Unit
points
Benchmark version
MathBench.ai v1.4 combined leaderboard; 200 problems (v1.3 100 + v1.4 100)
Category
mathematics
Direction
Higher is better
Sample
200
Source type
independent-evaluator
Evaluator
MathBench.ai exact-model results page
Status
active
Retrieved at
2026-10-17
Methodology
Independent evaluation. Exact model ID IQuest-Q1. The page reports thinking on and original BF16 weights on the evaluator's own NVIDIA H200 × 8 server. It reports 44/150 short answers correct and 14/50 Lean proofs correct, yielding 29/100 at 0.5 point per problem. Shared conditions: no token, turn or time limits; maximum vendor reasoning setting; Python tool for short-answer problems, Lean tool for proof problems; web search blocked; one attempt per problem. The evaluator states model time is server-dependent and not directly comparable. Model checkpoint hash, per-row execution date and confidence interval are not published.
Context
This is the current MathBench.ai v1.4 200-problem result, not the older MathBench-CN benchmark in other model cards. No confidence interval is reported; do not infer one from item counts.
Source MathBench.ai exact-model results page

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

The 100 most popular models of this category, 0 to 100, higher is more popular

20 of 101 models

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 20, 2026

IQuest-Q1Ornith 1.0 35B 43Apodex 1.1 Mini 43DiffusionGemma 26B A4B IT 43GLM-4.6V-Flash 43

Method changes in the timeline, a jump at these points is no market event:

  1. 1November 1, 2026: Value only with search or usage data, 30-day attention
  2. 2November 1, 2026: Method version 4 (common scale, shrinkage)
  3. 3November 9, 2026: New topics measurement V20 (daily quorum, short forms)

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

All specifications

Architecture

Model class
Mixture-of-experts language model for agentic tasks
Source: Model class
Parameters
About 320 billion total, about 15 billion active
Source: Parameters
Architecture
Mixture of experts with 256 total and 8 active experts
Source: Architecture

Input and output

Context window
524,288 tokens
Source: Context window

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Local weights with SGLang or vLLM deployment
Source: Access
License
IQuest-Q1 license
Source: License
Shutdown
None announced
no source

API

Model ID
IQuestLab/IQuest-Q1
Source: Model ID

Frequently asked questions about IQuest-Q1

How large is the context window of IQuest-Q1?

524,288 tokens. Separate limits may apply to input and output.

Context windowContext limit in tokens · higher is better
IQuest-Q1Rank 68 of 112524K
Solar Pro 4512K
Grok 4.7500K
Grok 4.6500K
Grok 4.5500K
GPT-5400K
GPT-5.4 mini400K

Can I run IQuest-Q1 locally?

Yes, the weights are open. With 320B parameters it needs a lot of memory, more a server than a laptop.

Stated by IQuest

Open weights
yes
License
IQuest-Q1 license
Parameters
320B
active per token
15B

Sources and data date

Show all 9 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.