Compare/Jamba 1.6 Mini vs Gemma 4 26B A4B (Reasoning)

Jamba 1.6 MinivsGemma 4 26B A4B (Reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

AI21 Labs

Jamba 1.6 Mini

Input
$0.2/M
Output
$0.4/M
Speed
183 tok/s
TTFT
0.77s
Google

Gemma 4 26B A4B (Reasoning)

Input
$0.13/M
Output
$0.4/M
Speed
TTFT

Winner by Category

Cheaper
Gemma 4 26B A4B (Reasoning)
Faster (tok/s)
Jamba 1.6 Mini
Lower Latency
Gemma 4 26B A4B (Reasoning)
Benchmarks (3-7)
Gemma 4 26B A4B (Reasoning)

Pricing Comparison

MetricJamba 1.6 MiniGemma 4 26B A4B (Reasoning)
Input ($/M tokens)$0.2$0.13
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
Jamba 1.6 Mini$0.24
Gemma 4 26B A4B (Reasoning)$0.17

Speed Comparison

Output Speed (tokens/s) — higher is better
Jamba 1.6 Mini
183 tok/s
Gemma 4 26B A4B (Reasoning)
Time to First Token (seconds) — lower is better
Jamba 1.6 Mini
0.77s
Gemma 4 26B A4B (Reasoning)

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
7.931.2
Coding Index
22.4
Math Index
GPQA Diamond
30.0%79.2%
MMLU-Pro
36.7%
LiveCodeBench
7.1%
AIME 2025
MATH-500
25.7%
Humanity's Last Exam
4.6%18.3%
SciCode
10.1%40.0%
IFBench
72.4%
TerminalBench
13.6%
Jamba 1.6 Mini3 wins
7 winsGemma 4 26B A4B (Reasoning)

Frequently Asked Questions

Which is cheaper, Jamba 1.6 Mini or Gemma 4 26B A4B (Reasoning)?

Gemma 4 26B A4B (Reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.20/M tokens vs $0.25/M for Jamba 1.6 Mini.

Which model performs better on benchmarks?

Gemma 4 26B A4B (Reasoning) wins 7 out of 12 benchmarks compared to 3 for Jamba 1.6 Mini. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Jamba 1.6 Mini generates tokens faster at 183 tok/s vs 0 tok/s. However, Gemma 4 26B A4B (Reasoning) has lower time-to-first-token (0.00s vs 0.77s).

When should I use Jamba 1.6 Mini vs Gemma 4 26B A4B (Reasoning)?

Choose based on your priorities: Gemma 4 26B A4B (Reasoning) for lower cost, Gemma 4 26B A4B (Reasoning) for stronger benchmark performance, and Jamba 1.6 Mini for faster generation. For latency-sensitive apps, check the TTFT comparison above.