Model Comparison
Jamba 1.5 Large
vs. Pixtral Large
Comparing 2 AI models · 11 benchmarks · AI21 Labs, Mistral
Recommended Pick
Mi Pixtral Large 11 metric wins Strongest on: Value, Output price, Blended price
Best Value
Pixtral Large
100.0 value score
21.6 reasoning / $3.00/1M
Lowest Price
Jamba 1.5 Large
$2.00/1M input price
Best Reasoning
Jamba 1.5 Large
24.5 reasoning score
Blends available reasoning benchmarks
Composite Indices
Higher is better; speed and price are normalized
Standard Benchmarks
Only benchmarks with data are shown
Differences That Matter
Best value
Pixtral Large has the strongest quality-to-price mix at 100.0 out of 100 value points.
Reasoning gap
Jamba 1.5 Large leads Pixtral Large by 2.9 points on reasoning.
Top-pick rationale
Pixtral Large wins 11 measurable categories, including Value, Output price, Blended price, Throughput.
Response Face-Off
Run one prompt through the selected models and compare response quality with live speed and cost context.
Jamba 1.5 Large
AI21 Labs
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Pixtral Large
Mistral
TTFT
—
Time
—
tok/s
—
Tokens
—
Cost
—
Which answer was more useful?
Full Comparison
| Metric | AI Jamba 1.5 Large | Top Pick Mi Pixtral Large |
|---|---|---|
| Pricing per 1M tokens | ||
| Input Cost | $2.00/1M | $2.00/1M |
| Output Cost | $8.00/1M | $6.00/1M |
| Blended (3:1) | $3.50/1M | $3.00/1M |
| Specifications | ||
| Organization | AI21 Labs | Mistral |
| Release Date | Aug 22, 2024 | Nov 18, 2024 |
| Performance & Speed | ||
| Throughput | — | 62.9 tok/s |
| TTFT | — | 628ms |
| Latency | — | 628ms |
| Composite Indices | ||
| Value Score | 97.4 | 100.0 |
| Reasoning Score | 24.5 | 21.6 |
| Intelligence | 10.7 | 14.0 |
| Math | — | 2.3 |
| Standard Benchmarks | ||
| GPQA | 42.7% | 50.5% |
| MMLU Pro | 57.2% | 70.1% |
| HLE | 4.0% | 3.6% |
| LiveCodeBench | 14.3% | 26.1% |
| MATH 500 | 60.6% | 71.4% |
| AIME 2025 | — | 2.3% |
| AIME (Original) | 4.7% | 7.0% |
| SciCode | 16.3% | 29.2% |
| LCR | — | 10.3% |
| IFBench | — | 34.5% |
| TAU-bench v2 | — | 36.5% |
Key Takeaways
Jamba 1.5 Large offers the best value at $2.00/1M, making it ideal for high-volume applications and cost-conscious projects.
Jamba 1.5 Large has the strongest reasoning profile with a 24.5 reasoning score, combining the available reasoning-heavy benchmarks.
All models support context windows of ∞+ tokens, suitable for processing lengthy documents and maintaining extended conversations.
When to Choose Each Model
Jamba 1.5 Large
- Cost-sensitive applications
- High-volume processing
- Complex reasoning tasks
- Research & analysis
Pixtral Large
- General-purpose AI
- Versatile applications
