Compare/Mistral Medium 3.5 vs Jamba 1.7 Large

Mistral Medium 3.5vsJamba 1.7 Large

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

Mistral

Mistral Medium 3.5

Input
$1.5/M
Output
$7.5/M
Speed
163 tok/s
TTFT
0.53s
AI21 Labs

Jamba 1.7 Large

Input
$2/M
Output
$8/M
Speed
56 tok/s
TTFT
0.97s

Winner by Category

Cheaper
Mistral Medium 3.5
Faster (tok/s)
Mistral Medium 3.5
Lower Latency
Mistral Medium 3.5
Benchmarks (7-5)
Mistral Medium 3.5

Pricing Comparison

MetricMistral Medium 3.5Jamba 1.7 Large
Input ($/M tokens)$1.5$2
Output ($/M tokens)$7.5$8
Cost for 1M input + 100K output tokens:
Mistral Medium 3.5$2.25
Jamba 1.7 Large$2.80

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Medium 3.5
163 tok/s
Jamba 1.7 Large
56 tok/s
Time to First Token (seconds) — lower is better
Mistral Medium 3.5
0.53s
Jamba 1.7 Large
0.97s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
39.210.9
Coding Index
35.47.8
Math Index
2.3
GPQA Diamond
74.8%39.0%
MMLU-Pro
57.7%
LiveCodeBench
18.1%
AIME 2025
2.3%
MATH-500
60.0%
Humanity's Last Exam
12.8%3.8%
SciCode
39.6%18.8%
IFBench
68.8%35.2%
TerminalBench
33.3%2.3%
Mistral Medium 3.57 wins
5 winsJamba 1.7 Large

Frequently Asked Questions

Which is cheaper, Mistral Medium 3.5 or Jamba 1.7 Large?

Mistral Medium 3.5 is cheaper overall. Its blended price (3:1 input/output ratio) is $3.00/M tokens vs $3.50/M for Jamba 1.7 Large.

Which model performs better on benchmarks?

Mistral Medium 3.5 wins 7 out of 12 benchmarks compared to 5 for Jamba 1.7 Large. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Mistral Medium 3.5 generates tokens faster at 163 tok/s vs 56 tok/s. Mistral Medium 3.5 also has lower time-to-first-token (0.53s vs 0.97s).

When should I use Mistral Medium 3.5 vs Jamba 1.7 Large?

Choose based on your priorities: Mistral Medium 3.5 for lower cost, Mistral Medium 3.5 for stronger benchmark performance, and Mistral Medium 3.5 for faster generation. For latency-sensitive apps, check the TTFT comparison above.