Noometry

Model comparison

Qwen3.8 Max vs video-SALMONN 2+

Qwen3.8 Max has enough public results to be ranked (#21); video-SALMONN 2+ does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Qwen3.8 Max Alibaba (Qwen)

56.0

Rank #21 Confirmed

video-SALMONN 2+ ByteDance Seed

40.8

Unranked Sparse

Summary

  • The widest gap is in multimodal, where video-SALMONN 2+ leads 41.7 to 36.9.

Side by side

Qwen3.8 Maxvideo-SALMONN 2+
ProviderAlibaba (Qwen)ByteDance Seed
Noometry Index56.040.8
Released2026-08-022025-06-18
WeightsProprietaryProprietary
Context window1M—
Max output131K—
Input $ / M tokens$2—
Output $ / M tokens$6—
Results tracked381

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Qwen3.8 Max: 52.3 (#30), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
DeepSWE57.5%—
LMArena WebDev1671—
FrontierSWE15.8%—
SciCode52.9%—
LMArena Coding1499—

Agentic & Tool Use Not comparable

Qwen3.8 Max: 42.6 (#17), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
τ²-bench Banking55.1%—
GDP.pdf23.2%—

Reasoning Not comparable

Qwen3.8 Max: 53.4 (#26), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
NYT Connections (extended)88.3%—
CritPt20%—
Chess Puzzles40%—
LMArena Hard Prompts1493—
Mystery Game Puzzles38%—
DTBench92%—
LMCA46.2%—
Epoch Capabilities Index156.69—

Math Not comparable

Qwen3.8 Max: 73.1 (#15), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
FrontierMath (Tiers 1-3)74.7%—
FrontierMath Tier 446.3%—
OTIS Mock AIME 2024-2025100%—
ProofBench58%—
LMArena Math1498—

Knowledge Not comparable

Qwen3.8 Max: 61.7 (#25), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
GPQA Diamond92.7%—
SimpleQA Verified47.3%—
LMArena Expert1504—

Multimodal video-SALMONN 2+ leads

Qwen3.8 Max: 36.9 (#70), video-SALMONN 2+: 41.7

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
LMArena Vision1314—
Video-MME—79.7%
Furniture Assembly20%—

Multilingual Not comparable

Qwen3.8 Max: 56.6 (#18), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
LMArena Non-English1468—
LMArena Chinese1537—
LMArena French1502—
LMArena German1489—
LMArena Japanese1466—
LMArena Korean1467—
LMArena Russian1478—
LMArena Spanish1495—

Instruction Following Not comparable

Qwen3.8 Max: 77.7 (#19), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
LMArena Instruction Following1478—

Long Context Not comparable

Qwen3.8 Max: 45.5 (#30), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
LMArena Longer Query1486—

Writing & Preference Not comparable

Qwen3.8 Max: 67.0 (#31), video-SALMONN 2+: —

BenchmarkQwen3.8 Maxvideo-SALMONN 2+
LMArena Text1480—
LMArena Creative Writing1478—
LMArena Multi-Turn1487—

Frequently asked questions

Is Qwen3.8 Max better than video-SALMONN 2+?

Qwen3.8 Max has enough public results to be ranked (#21); video-SALMONN 2+ does not yet, so treat this comparison as directional.

How many benchmarks do Qwen3.8 Max and video-SALMONN 2+ share?

0 benchmarks have published results for both models. Qwen3.8 Max has 38 scored results on Noometry and video-SALMONN 2+ has 1.

Related comparisons

Go deeper