MMODELYST
Models/Qwen3 VL 8B Instruct
MDL

Qwen3 VL 8B Instruct

Alibaba

Verified against Artificial Analysis · Jul 13, 2026
Capability
42
percentile index
Price /M
$0.18 / $0.7
in / out
Context
256K
tokens
Avg score
27.1
10 benchmarks
AA Intelligence
8.4
index
Speed
144 tok/s
TTFT 1.1s
Released
Oct 14, 2025
About

Qwen3 VL 8B Instruct is a open-weights model in the Qwen3 family from Alibaba. Benchmarked on 10 evals, averaging 27.1.

Benchmark scores · 10
avg 27.1 — higher is better
MMLU-Pro
68.6
GPQA Diamond
42.7
LiveCodeBench
33.2
IFBench
32.3
τ²-bench
29.2
AIME
27.3
SciCode
17.4
AA Long-Context Reasoning
15.3
Humanity's Last Exam
2.9
Terminal-Bench Hard
2.3
Details
PublisherAlibaba
FamilyQwen3
Parameters
License
WeightsOpen
ReleasedOct 14, 2025
Performance & price
Output speed144 tok/s
Latency (TTFT)1.1s
Price in / out$0.18 / $0.7 per 1M
Blended price$0.31 / 1M
Math index27.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.7/M