text model comparison
Gemini 3 Flash Preview vs Mistral Large 4
Gemini 3 Flash Preview and Mistral Large 4 are both current text models, from Google and Mistral AI. Gemini 3 Flash Preview is 29% cheaper per 1M input tokens than Mistral Large 4, $0.50 vs $0.70. On Arena Text, Gemini 3 Flash Preview scores 1473 Elo and Mistral Large 4 1432 Elo (Arena, measured October 28, 2026). Both accept about 1.05M tokens of context (1,048,576 and 1,000,000).
- Higher Arena Text
- Gemini 3 Flash Preview1473 Elo against 1432 Elo
- Lower price per 1M input tokens
- Gemini 3 Flash Preview$0.50 against $0.70
- Longer context window
- Gemini 3 Flash Preview1.05M tokens against 1M tokens
- Newer release
- Mistral Large 4Oct 2026 against Dec 2025
Data verified November 3, 2026 · Dataset 2026-11-03
Side by side
Gemini 3 Flash Preview and Mistral Large 4, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Gemini 3 Flash Preview | Mistral Large 4 |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.50 (better) | $0.70 |
| Price per 1M output tokens | $3 | $2.10 (better) |
| Independent benchmarks | ||
| Arena Text | 1473 Elo (#24 of 51) (better) | 1432 Elo (#40 of 51) |
| Arena WebDev | 1440 Elo (#37 of 45) | 1544 Elo (#32 of 45) (better) |
| FrontierMath Tiers 1-3 (v2) | 51.2% (#35 of 42) (better) | 46.3% (#36 of 42) |
| GPQA Diamond | 89.4% (#31 of 41) | 90.2% (#28 of 41) (better) |
| SimpleQA Verified | 66.8% (#10 of 38) (better) | 22.4% (#36 of 38) |
| Specs | ||
| Provider | Mistral AI | |
| Release date | December 17, 2025 | October 6, 2026 |
| Access | API only | API and open weights |
| Context window | 1,048,576 tokens | 1,000,000 tokens |
| Max output | 65,536 tokens | Not reported |
| Input | text, image, audio, video | text, image |
| Output | text | text |
Charts
Against every current text model
Where Gemini 3 Flash Preview and Mistral Large 4 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
On Arena Text, Gemini 3 Flash Preview ranks #24 and Mistral Large 4 #40 of 51 current models. Each bar is the share of current models it beats: on score, price and context.
Independent benchmarks
Arena Text
Gemini 3 Flash Preview:#24of 51
1,473 Elo · ahead of 54%
Mistral Large 4:#40of 51
1,432 Elo · ahead of 22%
Arena WebDev
Gemini 3 Flash Preview:#37of 45
1,440 Elo · ahead of 18%
Mistral Large 4:#32of 45
1,544 Elo · ahead of 30%
FrontierMath Tiers 1-3 (v2)
Gemini 3 Flash Preview:#35of 42
51.2% · ahead of 17%
Mistral Large 4:#36of 42
46.3% · ahead of 15%
GPQA Diamond
Gemini 3 Flash Preview:#31of 41
89.4% · ahead of 25%
Mistral Large 4:#28of 41
90.2% · ahead of 30%
SimpleQA Verified
Gemini 3 Flash Preview:#10of 38
66.8% · ahead of 76%
Mistral Large 4:#36of 38
22.4% · ahead of 5%
Price and context
Price per 1M input tokens
Gemini 3 Flash Preview:#17of 52
$0.50 · cheaper than 69%
Mistral Large 4:#19of 52
$0.70 · cheaper than 65%
Price per 1M output tokens
Gemini 3 Flash Preview:#21of 52
$3 · cheaper than 59%
Mistral Large 4:#16of 52
$2.10 · cheaper than 71%
Context window
Gemini 3 Flash Preview:#11of 64
1.05M tokens · longer than 67%
Mistral Large 4:#26of 64
1M tokens · longer than 22%
Quality against price
Gemini 3 Flash Preview scores 1,473 at $1.13; Mistral Large 4 scores 1,432 at $1.05 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Argon | $4 | 1,520 | |
| Claude Opus 5.5 | Anthropic | $8 | 1,509 |
| Muse Wonder | Meta | $8 | 1,507 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,504 |
| Gemini 3.8 Flash | $1.50 | 1,496 | |
| Muse Spark 1.3 | Meta | $2 | 1,495 |
| Claude Opus 5 | Anthropic | $10 | 1,492 |
| Kimi K3 | Moonshot Kimi | $6 | 1,488 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GPT-5.5 | OpenAI | $11 | 1,482 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,481 |
| GLM-5.3 | Z.ai | $2.15 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,477 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,477 |
| GPT-6 Astra | OpenAI | $20 | 1,476 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,476 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,467 |
| Grok 4.5 | xAI | $3 | 1,465 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,465 |
| Claude Sonnet 5 | Anthropic | $4 | 1,462 |
| GPT-6 Sol | OpenAI | $4 | 1,458 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,456 | |
| Grok 4.6 | xAI | $3 | 1,455 |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Grok 4.7 | xAI | $3 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,432 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,425 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Solar Pro 4 | Upstage | $0.52 | 1,388 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, Mistral Large 4 costs 1.0 times as much as Gemini 3 Flash Preview, at each provider's listed rates.
10M input and 2M output tokens
Mistral Large 4 costs 1.0× as much
- Gemini 3 Flash Preview
- $11
- Mistral Large 4
- $11.20
The same, with 9M of the input tokens cached
Gemini 3 Flash Preview costs 1.3× as much
- Gemini 3 Flash Preview
- $6.95
- Mistral Large 4
- $5.53
| Workload or rate | Gemini 3 Flash Preview | Mistral Large 4 |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $11 (better) | $11.20 |
| The same, with 9M of the input tokens cached | $6.95 | $5.53 (better) |
| Other listed rates | ||
| 1M input tokens, cached | $0.05 (better) | $0.07 |
| 1M input tokens, cached audio | $0.10 | Not listed |
| 1M input tokens, audio | $1 | Not listed |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Gemini 3 Flash Preview
Where it leads
- Lower price per 1M input tokens, $0.50 vs $0.70
- Lower cost for 10M input and 2M output tokens, $11 vs $11.20
- Higher Arena Text score, 1473 Elo vs 1432 Elo
- Higher FrontierMath Tiers 1-3 (v2) score, 51.2% vs 46.3%
- Higher SimpleQA Verified score, 66.8% vs 22.4%
- Accepts audio and video input
- Cheaper cached input, $0.05 vs $0.07 per 1M tokens
Best for
- Fast multimodal and agentic coding evaluations
Watch out for
- This preview endpoint may change before becoming stable and the published price varies by input modality
Mistral Large 4
Where it leads
- Lower price per 1M output tokens, $2.10 vs $3
- Higher Arena WebDev score, 1544 Elo vs 1440 Elo
- Higher GPQA Diamond score, 90.2% vs 89.4%
- Open weights you can run yourself
Best for
- Self-hosted or European data-residency deployments that want a frontier-scale multimodal model
- Coding and security agents where open weights and a low API price both matter
Watch out for
- The API model is still labelled a public preview, and the open weights are a further-trained build of the October 6 preview
- Businesses that sell it as a hosted model service need a separate commercial licence from Mistral
- Running the open weights moves cost to your own GPUs, which the token rates here do not represent
- Epoch AI measured 22.4% on SimpleQA Verified for the open-weight build, low for its size, so check factual recall on your own questions
From benchmark to production
Building on Gemini 3 Flash Preview or Mistral Large 4?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
Gemini 3 Flash Preview vs Mistral Large 4 FAQ
Which is cheaper, Gemini 3 Flash Preview or Mistral Large 4?
Gemini 3 Flash Preview is 29% cheaper per 1M input tokens than Mistral Large 4, $0.50 vs $0.70. For 10M input and 2M output tokens, Gemini 3 Flash Preview costs $11 and Mistral Large 4 $11.20 at standard rates.
Which is cheaper with prompt caching, Gemini 3 Flash Preview or Mistral Large 4?
Gemini 3 Flash Preview charges $0.05 per 1M cached input tokens, 90% below its standard input rate, and Mistral Large 4 $0.07, 90% below. With 9M of 10M input tokens cached and 2M output tokens, Gemini 3 Flash Preview costs $6.95 and Mistral Large 4 $5.53.
Which scores higher on independent benchmarks, Gemini 3 Flash Preview or Mistral Large 4?
Gemini 3 Flash Preview leads on Arena Text, 1473 Elo to 1432 Elo; Mistral Large 4 leads on Arena WebDev, 1544 Elo to 1440 Elo; Gemini 3 Flash Preview leads on FrontierMath Tiers 1-3 (v2), 51.2% to 46.3%. Scores are independent evaluations, not either vendor's launch figures.
Which has the larger context window, Gemini 3 Flash Preview or Mistral Large 4?
Both accept about 1.05M tokens of context (1,048,576 and 1,000,000).
How do Gemini 3 Flash Preview and Mistral Large 4 differ in features?
Gemini 3 Flash Preview takes text, image, audio and video input; Mistral Large 4 takes text and image.
Can I run Gemini 3 Flash Preview or Mistral Large 4 myself?
Mistral Large 4 is released as open weights you can run yourself; Gemini 3 Flash Preview is available through its provider's API only.
Further reading
More on Gemini 3 Flash Preview and Mistral Large 4
Related comparisons
- Claude Haiku 5.5 vs Gemini 3 Flash Preview
- Claude Haiku 5.5 vs Mistral Large 4
- DeepSeek-V4.1-Flash vs Gemini 3 Flash Preview
- DeepSeek-V4-Pro vs Mistral Large 4
- Gemini 3.8 Flash vs Gemini 3 Flash Preview
- Gemini 3.6 Flash vs Mistral Large 4
- Gemini 3.7 Flash vs Gemini 3 Flash Preview
- Gemini 3.8 Flash vs Mistral Large 4
- Gemini 3.1 Pro Preview vs Gemini 3 Flash Preview
- GLM-5.3 vs Mistral Large 4
- Gemini 3 Flash Preview vs GLM-5.3-Flash
- GPT-6 Luna vs Mistral Large 4
Production evaluation
Choosing between Gemini 3 Flash Preview and Mistral Large 4?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty