The AI arena is free today

Open Superagent

Mercury 3 vs Qwen3.5-0.8B

Mercury 3 leads the LLM Stats Score 36.1 to -6.7.

Inception · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Mercury 3 leads the overall LLM Stats Score 36.1 to -6.7, ranking #98 overall.

In the 4 individual benchmarks reported for both models, Mercury 3 wins 4; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Mercury 3

  • overall performance matters — it scores 36.1 and ranks #98 on LLM Stats
  • your work emphasizes reasoning and agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 4 exact shared results
  • you want the most recent training data — it shipped Oct 2026

Choose Qwen3.5-0.8B

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Mercury 3
Inception
Qwen3.5-0.8B
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
36.1
#98
-6.7
#388
Reasoning
34.8
#103
-4.0
#362
Agents
19.4
#84
-9.7
#210
Cost, coverage & limits
Benchmark wins
4 of 4
0 of 4
Input price
$0.10 / M
— / M
Output price
$0.35 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Mercury 3
Qwen3.5-0.8B
Long context
23.0#18
3.0#114
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

12 reported for Mercury 3 · 20 for Qwen3.5-0.8B

4 shared

Mercury 3 outperforms in 4 benchmarks (AA-LCR, GPQA, IFBench, Multi-Challenge), while Qwen3.5-0.8B is better at 0 benchmarks.

Mercury 3 significantly outperforms across most benchmarks.

Fri Oct 23 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Mercury 3 specifies input context (1,000,000 tokens). Only Mercury 3 specifies output context (131,072 tokens).

Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Alibaba Cloud / Qwen Team
Qwen3.5-0.8B
Input- tokens
Output- tokens
Fri Oct 23 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen3.5-0.8B supports multimodal inputs, whereas Mercury 3 does not.

Qwen3.5-0.8B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Mercury 3

Text
Images
Audio
Video

Qwen3.5-0.8B

Text
Images
Audio
Video

License

Usage and distribution terms

Mercury 3 is licensed under a proprietary license, while Qwen3.5-0.8B uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Mercury 3

Proprietary

Closed source

Qwen3.5-0.8B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Mercury 3 was released on 2026-10-19, while Qwen3.5-0.8B was released on 2026-03-02.

Mercury 3 is 8 months newer than Qwen3.5-0.8B.

Mercury 3

Oct 19, 2026

0 days ago

7mo newer
Qwen3.5-0.8B

Mar 2, 2026

7 months ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Mercury 3 and Qwen3.5-0.8B side-by-side, then vote on the output you prefer.

Mercury 3
✓ Preferred
Qwen3.5-0.8B
Open in Playground

FAQ

Common questions about Mercury 3 vs Qwen3.5-0.8B.

Which is better, Mercury 3 or Qwen3.5-0.8B?

Mercury 3 leads the LLM Stats Score 36.1 to -6.7. Mercury 3 is made by Inception and Qwen3.5-0.8B is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Mercury 3 compare to Qwen3.5-0.8B in benchmarks?

Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%. Qwen3.5-0.8B scores MMLU-Redux: 59.5%, Global PIQA: 59.4%, C-Eval: 50.5%, MMMLU: 44.3%, IFEval: 44.0%.

What are the context window sizes for Mercury 3 and Qwen3.5-0.8B?

Mercury 3 supports 1.0M tokens and Qwen3.5-0.8B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Mercury 3 and Qwen3.5-0.8B?

Key differences include LLM Stats Score (36.1 vs -6.7), multimodal support (no vs yes), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Mercury 3 and Qwen3.5-0.8B?

Mercury 3 is developed by Inception and Qwen3.5-0.8B is developed by Alibaba Cloud / Qwen Team.

Related comparisons