The Model Index
Up to four models

Gemma 4 26B A4B vs Qwen3.5-35B-A3B

On the index (GPT-4 = 100), Gemma 4 26B A4B scores 135 and Qwen3.5-35B-A3B 135. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Gemma 4 26B A4B
Presets
Gemma 4 26B A4B
135119–151
WeightsOpen
ReleasedApr 2026
Price in / out$0.076 / $0.26
Context262K
Core tests taken1 of 9
Qwen3.5-35B-A3B
135118–151
WeightsOpen
ReleasedFeb 2026
Price in / out$0.14 / $1.0
Context262K
Core tests taken1 of 9

Gemma 4 26B A4B and Qwen3.5-35B-A3B are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests, and costs 2.9× less.

Test by testthird-party results

Gemma 4 26B A4BQwen3.5-35B-A3B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestGemma 4 26B A4BQwen3.5-35B-A3B
Reasoning & knowledge
GPQA Diamond (Epoch AI)73.2%83.5%
Maths
AIME-style maths (OTIS mock)82.2%70.0%
Agents
DTBench74.9%80.0%
LMCA29.7%29.5%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG