Skip to main content
BenchLM
Data

Data as of October 27, 2026 · How the score is built

CurrentOpen WeightReasoning

Released Aug 26, 2026262K contextQwen3.8-Flash-Next model card

Qwen3.8-Flash-Next

Decision readingQwen3.8-Flash-Next scores 63 out of 100 and ranks #48 of 230. This profile shows 25 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #12. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.

Released Aug 26, 2026 — see all recent releases

Find alternativesCompare Qwen3.8-Flash-Next
Share or export
Share on XLinkedIn
Social cardBenchmarks CSVAPI/MCP query guide

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

63/100

field median 50.2#48 of 230 ranked models

Public

#48of 230

Verified —

Price

Self-hosted; infrastructure cost varies

input median $0.75No comparable first-party hosted token rate

Speed

52tok/s

field median 96 tok/sFirst token 40.81 s

Context

262Ktokens

field median 256,000Maximum output length is tracked separately

Strongest published evidence

Multimodal & Grounded ranks #12. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Validate before choosing

25 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.

Source-linked · 25 displayable benchmark rows

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #19 of 134Percentile 86thWeight 22%6 benchmarksVerified
65.0
CodingRank #43 of 155Percentile 73rdWeight 20%5 benchmarksVerified
51.9
ReasoningWeight 17%0 benchmarksNot measured
Not measured
MultimodalRank #12 of 58Percentile 81stWeight 12%9 benchmarksVerified
86.1
KnowledgeRank #53 of 189Percentile 72ndWeight 12%4 benchmarksVerified
59.3
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingRank #24 of 156Percentile 85thWeight 5%1 benchmarkVerified
91.2
MathWeight 5%0 benchmarksNot measured
Not measured

25 of 774 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic6/6 verified
  2. Coding5/5 verified
  3. ReasoningNot measured
  4. Multimodal9/9 verified
  5. Knowledge4/4 verified
  6. MultilingualNot measured
  7. Inst. Following1/1 verified
  8. MathNot measured
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

Qwen3.8-Flash-Next category percentile values

  • Agentic86th percentile
  • Coding73rd percentile
  • ReasoningNot eligible
  • Multimodal81st percentile
  • Knowledge72nd percentile
  • MultilingualNot eligible
  • Instruction following85th percentile
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#19/134
  2. Coding#43/155
  3. ReasoningNot ranked
  4. Multimodal#12/58
  5. Knowledge#53/189
  6. MultilingualNot ranked
  7. Inst. Following#24/156
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding5 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench ProScore62.5%Versus best verified row

Best verified: Claude Opus 5.5 · 89.9%

Gap27.4 behindWeight26% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
DeepSWEScore58.7%Versus best verified row

Best verified: Muse Wonder Full · 79.0%

Gap20.3 behindWeight15% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
SWE MultilingualScore81%Versus best verified row

Best verified: Claude Opus 5.5 · 93.9%

Gap12.9 behindWeight5% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
NL2RepoScore48.1%Versus best verified row

Best verified: DeepSeek V4.1 Flash 1017 · 68.2%

Gap20.1 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
LiveCodeBench v6Score91.9%Versus best verified row

Best verified: Sakana Fugu-Ultra · 93.2%

Gap1.3 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
Agentic6 rows
Agentic benchmark values, best verified comparison, weight, and source status
JobBenchScore55.7%Versus best verified row

Best verified: Muse Wonder Full · 75.3%

Gap19.6 behindWeight6% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
Agents' Last ExamScore51.2%Versus best verified row

Best verified: GPT-6.1 Terra · 60.0%

Gap8.8 behindWeight3% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
Toolathlon-VerifiedScore73.5%Versus best verified row

Best verified: Claude Opus 5 · 80.6%

Gap7.1 behindWeight3% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
CoWorkBenchScore73.9%Versus best verified row

Best verified: Qwen3.8-Omni-Flash · 75.3%

Gap1.4 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
AndroidWorldScore84.5%Versus best verified row

Best verified: Qwen3.8-Omni-Flash · 87.1%

Gap2.6 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
OSWorld 2.0Score19.4%Versus best verified row

Best verified: Kimi K3.1 Pro · 79.6%

Gap60.2 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
Multimodal9 rows
Multimodal benchmark values, best verified comparison, weight, and source status
CharXivCharXiv ReasoningScore90.6%Versus best verified row

Best verified: Qwen3.8 Max · 93.5%

Gap2.9 behindWeightWeighted 20%
Provider exact
Qwen3.8-Flash-Next model card
ExtractBench (LlamaIndex)ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)Score89.88%Versus best verified row

Best verified: Claude Sonnet 5.5 · 94.68%

Gap4.8 behindWeightDisplay only
Benchmark exact
ExtractBench leaderboard, October 25, 2026 snapshot (LlamaIndex)
Vision2WebScore64.0%Versus best verified row

Best verified: Qwen3.8 Max · 69.0%

Gap5 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
ERQAScore72.3%Versus best verified row

Best verified: Qwen3.8 Max · 77.8%

Gap5.5 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
LVBenchScore76.6%Versus best verified row

Best verified: Gemini 4 Argon · 91.7%

Gap15.1 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
RealWorldQAScore88.5%Versus best verified row

Best verified: Qwen3.8-Flash-Next · 88.5%

GapBest verifiedWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
MathVisionScore90.6%Versus best verified row

Best verified: Qwen3.8 Max · 95.2%

Gap4.6 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
MathVision w/ PythonMathVision with PythonScore95.7%Versus best verified row

Best verified: Kimi K3 · 97.8%

Gap2.1 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
CharXiv w/o toolsCharXiv Reasoning without toolsScore84.6%Versus best verified row

Best verified: Kimi K3.1 Pro · 89%

Gap4.4 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
Knowledge4 rows
Knowledge benchmark values, best verified comparison, weight, and source status
HLEHumanity's Last ExamScore35.9%Versus best verified row

Best verified: Kimi K3.1 Pro · 70%

Gap34.1 behindWeight44% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
HLE w/o toolsHumanity's Last Exam without toolsScore35.9%Versus best verified row

Best verified: Claude Opus 5.5 · 64.4%

Gap28.5 behindWeight7% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
GPQAGraduate-Level Google-Proof Q&AScore91.7%Versus best verified row

Best verified: GPT-6 Astra · 96%

Gap4.3 behindWeight3% ref. weight
Provider exact
Qwen3.8-Flash-Next model card
GPQA-DGPQA DiamondScore91.7%Versus best verified row

Best verified: GPT-6 Astra · 96.0%

Gap4.3 behindWeightDisplay only
Provider exact
Qwen3.8-Flash-Next model card
Inst. Following1 row
Inst. Following benchmark values, best verified comparison, weight, and source status
IFBenchInstruction Following BenchmarkScore81.3%Versus best verified row

Best verified: Flint · 89.2%

Gap7.9 behindWeightWeighted 70%
Provider exact
Qwen3.8-Flash-Next model card

Bars run 0–100; the dark tick marks the best source-verified value

All 25 rows

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. Aug 26, 2026 · you are here

    Qwen3.8-Flash-Next

    Score 63.0 · Price not listed

experimental-preview · Next

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
Qwen/Qwen3.8-Flash-NextQwen3.8-Flash-Next model card
Context window
262KQwen3.8-Flash-Next model card
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
Not sourced yet
Output modalities
Not sourced yet
Parameters
Not sourced yet
Availability
Qwen publishes the BF16 post-trained checkpoint on Hugging Face under the Qwen Community 1.0 license. The model card documents native text, image, and video input, reasoning-effort controls, and a 262,144-token native context window that can be extended to 1,000,000 tokens with YaRN. Qwen Cloud offers a separate production Qwen3.8-Flash model based on this architecture; this row does not inherit that sibling's features or pricing.
Cloud regions
Not tracked yet
Lifecycle
Current
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Not documented in the pricing recordQwen3.8-Flash-Next model card
Self-host
Qwen3.8-Flash-Next needs ~160GB VRAM (2× NVIDIA H100 (80GB)).
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Qwen3.8-Flash-Next ranks #48 of 230 on the public leaderboard with a score of 62.99/100. It does not yet have enough sourced coverage for a verified position.

Qwen3.8-Flash-Next is a open weight model with a 262K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Qwen publishes the BF16 post-trained checkpoint on Hugging Face under the Qwen Community 1.0 license. The model card documents native text, image, and video input, reasoning-effort controls, and a 262,144-token native context window that can be extended to 1,000,000 tokens with YaRN. Qwen Cloud offers a separate production Qwen3.8-Flash model based on this architecture; this row does not inherit that sibling's features or pricing.

Official exact-value snapshot from Qwen's August 26, 2026 Qwen3.8-Flash-Next model card and technical report. We map only the post-trained model-card rows that match existing protocols, keep the 262,144-token native context instead of the optional 1M YaRN extension, and preserve paired no-Code-Interpreter and Code-Interpreter visual scores separately. DeepSWE 1.1 uses the best result across Claude Code and mini-SWE-agent, SWE-bench Pro uses Qwen's corrected-task Claude Code run, and the remaining harness-specific agent results stay display-only. ClawEval-MM, RecreationBench, and the technical report's 14 base-model benchmarks remain outside this post-trained row rather than being collapsed into non-equivalent or cross-stage fields.

25 of 774 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Multimodal & Grounded at #12, while its lowest eligible position is Knowledge at #53. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Last updated October 27, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Qwen3.8-Flash-Next
API / mo$0
Self-host / mo$6,990
Break-even—
Model the full break-even

Questions

How does Qwen3.8-Flash-Next perform overall in AI benchmarks?

Qwen3.8-Flash-Next ranks #48 out of 230 models on the public BenchAlign leaderboard, with a score of 62.99/100. Its evidence status is Estimated, and this profile shows 25 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Qwen3.8-Flash-Next good for knowledge and understanding?

Qwen3.8-Flash-Next ranks #53 out of 189 eligible models for knowledge and understanding, with a public category score of 59.3/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Qwen3.8-Flash-Next good for coding and programming?

Qwen3.8-Flash-Next ranks #43 out of 155 eligible models for coding and programming, with a public category score of 51.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Qwen3.8-Flash-Next good for agentic tool use and computer tasks?

Qwen3.8-Flash-Next ranks #19 out of 134 eligible models for agentic tool use and computer tasks, with a public category score of 65/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Qwen3.8-Flash-Next good for multimodal and grounded tasks?

Qwen3.8-Flash-Next ranks #12 out of 58 eligible models for multimodal and grounded tasks, with a public category score of 86.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Qwen3.8-Flash-Next good for instruction following?

Qwen3.8-Flash-Next ranks #24 out of 156 eligible models for instruction following, with a public category score of 91.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Qwen3.8-Flash-Next open source?

Qwen3.8-Flash-Next is an open-weight model from Alibaba. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.

Does Qwen3.8-Flash-Next have full benchmark coverage on BenchLM?

No. Qwen3.8-Flash-Next currently has 40 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Qwen3.8-Flash-Next?

Qwen3.8-Flash-Next has a documented context window of 262K. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Watch Qwen3.8-Flash-Next in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 6,100+ subscribers.

Compare Qwen3.8-Flash-Next with every tracked model999 comparisons