Skip to main content
Radar

Every change to the models you run, with its source and its date. Releases, price changes, retirements, API changes, and incidents.Every change to the models you run, with its source.

Follow model changes
BenchLM

Mistral Medium 3.5 128B vs Qwen3.8 Max

Decision reading

Qwen3.8 Max has the higher public score, 71.76 versus 42.49, and the 90% score intervals do not overlap.

4 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Mistral logo
Model A
Mistral Medium 3.5 128B

Mistral

42.49/100

Estimated · Public rank #174

90% interval 31.0–54.0

Alibaba logo
Model B
Qwen3.8 Max

Alibaba

71.76/100

Supported · Public rank #11

90% interval 68.1–75.4

Updated September 15, 2026. Rank says Qwen3.8 Max is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export

Share on XLinkedInSocial cardCSVJSON

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Qwen3.8 Max

    Qwen3.8 Max leads on the public agentic lane, 67.3 to 22, with Supported evidence for both models and non-overlapping 90% intervals.

    Confidence: stronger

  • Long documents

    Prompts that approach the documented context limit

    Qwen3.8 Max

    Qwen3.8 Max has the larger documented context window.

    Confidence: documented

Show secondary and unsupported calls

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    Mistral Medium 3.5 128B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: rate-fallback

  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
4
Mistral Medium 3.5 128B only
3
Qwen3.8 Max only
56
Like-for-like categories
2 / 8

2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Mistral Medium 3.5 128B
22.0
Supported · #151/153
Qwen3.8 Max
67.3
Supported · #9/153
Basis
BenchAlign lane · 3 vs 15 public rows
Reading
Qwen3.8 Max leads

Knowledge

Like-for-like
Mistral Medium 3.5 128B
40.5
Supported · #132/183
Qwen3.8 Max
68.8
Supported · #17/183
Basis
BenchAlign lane · 2 vs 6 public rows
Reading
Qwen3.8 Max leads

Coding

Directional only
Mistral Medium 3.5 128B
39.2
Estimated · #121/152
Qwen3.8 Max
60.8
Supported · #20/152
Basis
BenchAlign lane · 2 vs 12 public rows
Reading
Directional only

Instruction following

Directional only
Mistral Medium 3.5 128B
84.0
#48/123
Qwen3.8 Max
90.7
#18/123
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Directional only

Reasoning

Not comparable
Mistral Medium 3.5 128B
68.6
Unranked · 2 rankable rows
Qwen3.8 Max
86.5
Unranked · 2 rankable rows
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Math

Not comparable
Mistral Medium 3.5 128B
Not ranked
Qwen3.8 Max
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multilingual

Not comparable
Mistral Medium 3.5 128B
Not ranked
Qwen3.8 Max
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Multimodal

Not comparable
Mistral Medium 3.5 128B
55.6
Unranked · 1 rankable row
Qwen3.8 Max
87.4
#5/48
Basis
Provisional lane · 0 vs 2 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Mistral Medium 3.5 128B
$0.00525
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Mistral Medium 3.5 128B
$0.0975
Fits in one request
Qwen3.8 Max
API rate not published
Fits in one request

Qwen3.8 Max has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Mistral Medium 3.5 128B
$0.405
Fits in one request
Cached input priced at the published list-input rate
Qwen3.8 Max
API rate not published
Fits in one request
Cached-input rate unavailable

Mistral Medium 3.5 128B has no published cached-input rate, so cached tokens use its listed input rate. Qwen3.8 Max has no comparable published API token rate.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Mistral Medium 3.5 128B

Not published

Qwen3.8 Max

No comparable hosted API rate

Alibaba Cloud Model Studio pricing

Documented inputs

Mistral Medium 3.5 128B

Not sourced

Qwen3.8 Max

Not sourced

Documented outputs

Mistral Medium 3.5 128B

Not sourced

Qwen3.8 Max

Not sourced

Provider availability

Mistral Medium 3.5 128B

Not sourced

Qwen3.8 Max

Not sourced

Reasoning profile

Mistral Medium 3.5 128B

Reasoning

Qwen3.8 Max

Reasoning

Weight access

Mistral Medium 3.5 128B

Open Weight

Qwen3.8 Max

Open Weight

License

Mistral Medium 3.5 128B

Open Weight

Qwen3.8 Max

Open Weight

Release date

Mistral Medium 3.5 128B

2026-04-29

Qwen3.8 Max

2026-08-03

If you already use one of these models
Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Qwen3.8 Max has the higher public score, 71.76 versus 42.49, and the 90% score intervals do not overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Qwen3.8 Max has the larger documented window (1M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence63 rows

Agentic

  • τ³-bench results

    Mistral Medium 3.5 128B91.4%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Gert Labs

    Mistral Medium 3.5 128B39.10%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Mistral Medium 3.5 128B39.0%
    Source
    Qwen3.8 Max67.4%
    Source

    Qwen3.8 Max leads this result

  • Terminal-Bench 2.1

    Mistral Medium 3.5 128B—
    Qwen3.8 Max86.6%
    Source

    Not directly comparable

  • CoWorkBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max74.8%
    Source

    Not directly comparable

  • JobBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max53.4%
    Source

    Not directly comparable

  • skillsBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max70.2%
    Source

    Not directly comparable

  • Agents' Last Exam

    Mistral Medium 3.5 128B—
    Qwen3.8 Max52.4%
    Source

    Not directly comparable

  • AutomationBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max27.3%
    Source

    Not directly comparable

  • Toolathlon-Verified

    Mistral Medium 3.5 128B—
    Qwen3.8 Max72.5%
    Source

    Not directly comparable

  • WideResearch

    Mistral Medium 3.5 128B—
    Qwen3.8 Max81.9%
    Source

    Not directly comparable

  • HLE w/ tools

    Mistral Medium 3.5 128B—
    Qwen3.8 Max56.2%
    Source

    Not directly comparable

  • OSWorld-Verified

    Mistral Medium 3.5 128B—
    Qwen3.8 Max86.1%
    Source

    Not directly comparable

  • OSWorld 2.0

    Mistral Medium 3.5 128B—
    Qwen3.8 Max19.4%
    Source

    Not directly comparable

  • WebArena-Verified

    Mistral Medium 3.5 128B—
    Qwen3.8 Max66.8%
    Source

    Not directly comparable

  • AndroidWorld

    Mistral Medium 3.5 128B—
    Qwen3.8 Max85.3%
    Source

    Not directly comparable

  • MobileWorld

    Mistral Medium 3.5 128B—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Mistral Medium 3.5 128B77.6%
    Source
    Qwen3.8 Max—

    Not directly comparable

  • SWE-bench (Vals)

    Mistral Medium 3.5 128B66.4%
    Source
    Qwen3.8 Max85.6%
    Source

    Qwen3.8 Max leads this result

  • Terminal-Bench 2.1

    Mistral Medium 3.5 128B—
    Qwen3.8 Max86.6%
    Source

    Not directly comparable

  • SWE-bench Pro

    Mistral Medium 3.5 128B—
    Qwen3.8 Max67.7%
    Source

    Not directly comparable

  • DeepSWE

    Mistral Medium 3.5 128B—
    Qwen3.8 Max56.6%
    Source

    Not directly comparable

  • NL2Repo

    Mistral Medium 3.5 128B—
    Qwen3.8 Max55.9%
    Source

    Not directly comparable

  • FrontierSWE

    Mistral Medium 3.5 128B—
    Qwen3.8 Max73.5%
    Source

    Not directly comparable

  • MLS-Bench Lite

    Mistral Medium 3.5 128B—
    Qwen3.8 Max41.0%
    Source

    Not directly comparable

  • PaperBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max93.0%
    Source

    Not directly comparable

  • VulcanBench v3

    Mistral Medium 3.5 128B—
    Qwen3.8 Max81.2%
    Source

    Not directly comparable

  • OpenHarmony Bench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max60.8%
    Source

    Not directly comparable

  • FrontierSWE v2

    Mistral Medium 3.5 128B—
    Qwen3.8 Max15.8%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Mistral Medium 3.5 128B—
    Qwen3.8 Max87.9%
    Source

    Not directly comparable

Reasoning

  • MRCRv2

    Mistral Medium 3.5 128B—
    Qwen3.8 Max92.9%
    Source

    Not directly comparable

  • LongBench v2

    Mistral Medium 3.5 128B—
    Qwen3.8 Max66.3%
    Source

    Not directly comparable

Knowledge

  • GPQA Diamond (Vals)

    Mistral Medium 3.5 128B34.8%
    Source
    Qwen3.8 Max93.7%
    Source

    Qwen3.8 Max leads this result

  • MMLU-Pro (Vals)

    Mistral Medium 3.5 128B75.3%
    Source
    Qwen3.8 Max88.6%
    Source

    Qwen3.8 Max leads this result

  • GPQA

    Mistral Medium 3.5 128B—
    Qwen3.8 Max92.6%
    Source

    Not directly comparable

  • GPQA-D

    Mistral Medium 3.5 128B—
    Qwen3.8 Max92.6%
    Source

    Not directly comparable

  • HLE

    Mistral Medium 3.5 128B—
    Qwen3.8 Max43.6%
    Source

    Not directly comparable

  • HLE w/o tools

    Mistral Medium 3.5 128B—
    Qwen3.8 Max43.6%
    Source

    Not directly comparable

Multimodal

  • MMMU-Pro

    Mistral Medium 3.5 128B—
    Qwen3.8 Max82.3%
    Source

    Not directly comparable

  • MathVision

    Mistral Medium 3.5 128B—
    Qwen3.8 Max95.2%
    Source

    Not directly comparable

  • MathVision w/ Python

    Mistral Medium 3.5 128B—
    Qwen3.8 Max97.7%
    Source

    Not directly comparable

  • BabyVision

    Mistral Medium 3.5 128B—
    Qwen3.8 Max82.0%
    Source

    Not directly comparable

  • BabyVision w/ Python

    Mistral Medium 3.5 128B—
    Qwen3.8 Max91.3%
    Source

    Not directly comparable

  • ZeroBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max24.0%
    Source

    Not directly comparable

  • ZeroBench w/ Python

    Mistral Medium 3.5 128B—
    Qwen3.8 Max49.0%
    Source

    Not directly comparable

  • MedXpertQA (MM)

    Mistral Medium 3.5 128B—
    Qwen3.8 Max80.4%
    Source

    Not directly comparable

  • ScreenSpot Pro

    Mistral Medium 3.5 128B—
    Qwen3.8 Max84.5%
    Source

    Not directly comparable

  • Vision2Web

    Mistral Medium 3.5 128B—
    Qwen3.8 Max69.0%
    Source

    Not directly comparable

  • CharXiv w/o tools

    Mistral Medium 3.5 128B—
    Qwen3.8 Max88.4%
    Source

    Not directly comparable

  • CharXiv

    Mistral Medium 3.5 128B—
    Qwen3.8 Max93.5%
    Source

    Not directly comparable

  • OmniDocBench 1.5

    Mistral Medium 3.5 128B—
    Qwen3.8 Max92.1%
    Source

    Not directly comparable

  • OCRBench V2

    Mistral Medium 3.5 128B—
    Qwen3.8 Max74.2%
    Source

    Not directly comparable

  • CC-OCR

    Mistral Medium 3.5 128B—
    Qwen3.8 Max79.6%
    Source

    Not directly comparable

  • RealWorldQA

    Mistral Medium 3.5 128B—
    Qwen3.8 Max88.0%
    Source

    Not directly comparable

  • ERQA

    Mistral Medium 3.5 128B—
    Qwen3.8 Max77.8%
    Source

    Not directly comparable

  • SimpleVQA

    Mistral Medium 3.5 128B—
    Qwen3.8 Max75.0%
    Source

    Not directly comparable

  • PerceptionBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max63.5%
    Source

    Not directly comparable

  • Video-MME (with subtitle)

    Mistral Medium 3.5 128B—
    Qwen3.8 Max90.4%
    Source

    Not directly comparable

  • VideoMMMU

    Mistral Medium 3.5 128B—
    Qwen3.8 Max88.7%
    Source

    Not directly comparable

  • MMVU

    Mistral Medium 3.5 128B—
    Qwen3.8 Max82.4%
    Source

    Not directly comparable

  • MLVU (M-Avg)

    Mistral Medium 3.5 128B—
    Qwen3.8 Max90.8%
    Source

    Not directly comparable

  • LVBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max81.8%
    Source

    Not directly comparable

Instruction following

  • IFBench

    Mistral Medium 3.5 128B—
    Qwen3.8 Max82.8%
    Source

    Not directly comparable

Questions

Which is better, Mistral Medium 3.5 128B or Qwen3.8 Max?

Qwen3.8 Max has the higher public score, 71.76 versus 42.49, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Mistral Medium 3.5 128B or Qwen3.8 Max?

Qwen3.8 Max scores higher for coding on the public lane, 60.8 to 39.2. Mistral Medium 3.5 128B is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, Mistral Medium 3.5 128B or Qwen3.8 Max?

Qwen3.8 Max leads the public agentic tasks lane, 67.3 to 22, with Supported evidence for both models and non-overlapping 90% intervals.

Which costs less, Mistral Medium 3.5 128B or Qwen3.8 Max?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Mistral Medium 3.5 128B or Qwen3.8 Max?

Qwen3.8 Max has the larger documented context window: 1M, compared with 256K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 15, 2026

Watch Mistral Medium 3.5 128B vs Qwen3.8 Max

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.