Standard Compute
Model comparison 2026

Devstral 2 vs Gemini 3.8 Flash

Devstral 2
Mistral · Balanced · Open weights
$0.88/1M · 262K ctx
Gemini 3.8 Flash
Google · Balanced · Proprietary
$1.65/1M · 1.0M ctx

Community vote

Pick a winner in each dimension. You can change your vote any time.

Output Quality
Correctness and depth of what it produces
Agentic Ability
Tool calls, instruction-following, and multi-step tasks
Speed
Tokens per second and time-to-first-token
Value for money
How much capability you get per dollar
Reliability
Consistent results: fewer refusals, loops and format breaks

Specs and pricing side by side

Spec
Devstral 2
Gemini 3.8 Flash
Maker
Mistral
Google
Blended price / 1M
$0.88
$1.65
Input / output
$0.40 in · $2.00 out / 1M tokens
$0.75 in · $3.75 out / 1M tokens
Context window
262K
1.0M
Open weights
Yes
No
Tool use
Yes
Yes
Reasoning
No
Yes
Output Quality
7.8
9.1
Agentic Ability
8.6
8.9
Speed
8.2
9.2
Value for money
8.8
8.8
Reliability
8.7
8.9

Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).

Verdict: Devstral 2 or Gemini 3.8 Flash?

Updated 2026-10-13

Choose Devstral 2 if you want dedicated open-weight coding agents. Choose Gemini 3.8 Flash if you want high-throughput agents and Gemini CLI users who want speed and big context.

In our editorial scoring, Gemini 3.8 Flash leads in 4 of five dimensions (output quality, agentic ability, speed and reliability), while Devstral 2 leads in 0. On price, Devstral 2 runs about $0.88 per 1M tokens (blended) and is open-weight; Gemini 3.8 Flash is about $1.65 and proprietary.

Where Devstral 2 falls short
  • Narrower than a general model
  • Behind frontier on hard reasoning
Full Devstral 2 breakdown →
Where Gemini 3.8 Flash falls short
  • Price doubles to $1.50/$7.50 on January 1, 2027
  • Weak on long terminal tasks (19.1% on Terminal-Bench 4.0)
Full Gemini 3.8 Flash breakdown →

The agent matters as much as the model. Compare AI agents →

Current Claude, GPT, Gemini and open models are included with Standard Compute

Standard Compute

Current frontier models Claude Opus 5.5 · Claude Sonnet 5.5

Your agents never stop.
Your bill never grows.

Frontier models when it counts. Efficient models when it doesn’t. The most intelligence per dollar. One flat bill.

Plans from $19/mo · cancel anytime · 7-day fair refund

7-day fair refund No credit card needed Billing by Stripe1,800+ agent users

Related comparisons