Head-to-Head Model Comparison

Command R+ vs Jamba 1.5 Large

Benchmarks, API Token Pricing, Context Window & Speed Comparison

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale

Changez et Comparez les Modèles

Select any AI models from our verified benchmark database to generate live side-by-side matrices.

Command R+Profile

Jamba 1.5 LargeProfile

Multi-Model Arena Stack:

5-Model Matrix Workbench

Popular Matchups:

Cohere

Command R+

Modèle de Base à Poids Ouverts

Command R+ de Cohere est un modèle d’IA conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, offrant une fenêtre de contexte de 128K, une vitesse de 65 tokens/s, un indice d’intelligence de

Intelligence Index48 / 100

Input Token:

$2.50 / 1M

Output Token:

$10.00 / 1M

Context Window:

128K tokens

SWE-bench Verified:

41.5%

AI21

Jamba 1.5 Large

Modèle de Base à Poids Ouverts

Jamba 1.5 Large de AI21 est un modèle d’IA conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, offrant une fenêtre de contexte de 256K, une vitesse de 82 tokens/s, un indice d’intelligence

Intelligence Index42 / 100

Input Token:

$2.00 / 1M

Output Token:

$8.00 / 1M

Context Window:

256K tokens

SWE-bench Verified:

41.2%

Différences Clés en un Coup d’Œil

Jamba 1.5 Large is 1.3x cheaper for API usage (input + output tokens combined).
Jamba 1.5 Large has a larger context window (256K vs 128K tokens).
Jamba 1.5 Large is faster at 82 tok/s vs 65 tok/s.
Command R+ leads on SWE-bench coding (41.5% vs 41.2%).

Need definitions for token pricing, context, or benchmarks?Explore AI Glossary →

Caractéristique	Command R+	Jamba 1.5 Large
Intelligence Index Composite reasoning & knowledge score (0-100)	48	42
Provider	Cohere	AI21
Input Price Cost per million input tokens	$2.50 / 1M	$2.00 / 1M
Output Price Cost per million output tokens	$10.00 / 1M	$8.00 / 1M
Blended Price Weighted 7:2:1 cache:input:output per 1M	$2.02 / 1M	$1.55 / 1M
Context Window Maximum input + output tokens	128K tokens~192 A4 pages of text	256K tokens~384 A4 pages of text
Max Output Tokens Per single request	8K	4K
Throughput Speed Tokens generated per second	65 tok/s	82 tok/s
SWE-bench Verified Real-world software engineering	41.5%	41.2%
GPQA Diamond Graduate-level reasoning	56.5%	51%
Cached Input Price Prompt caching discount per 1M tokens	$0.75 / 1M	$0.50 / 1M

Qui gagne où ?

At-a-glance decision framework

Code

Command R+

+0.3% SWE-bench lead

Coût

Jamba 1.5 Large

1.3x cheaper monthly runtime

Vitesse

Jamba 1.5 Large

+26% faster generation

Contexte

Jamba 1.5 Large

256K tokens window

Scores de Benchmarks Vérifiés

Official evaluation metrics verified by independent third-party research labs.

Command R+Jamba 1.5 Large

SWE-bench Verified (Autonomous Coding)

Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.

41.5%vs41.2%

GPQA Diamond (Doctorate-Level Science & Math)

Challenging questions created by domain experts to test complex PhD-level reasoning.

56.5%vs51%

MMLU-Pro (Multi-task Language Understanding)

Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.

78.5%vs70.2%

LMSYS Chatbot Arena Elo

Crowdsourced human preference evaluation based on blind, head-to-head model battles.

1300ptsvs1275pts

Humanity's Last Exam (Frontier Expert Knowledge)

Extremely difficult, closed-ended questions spanning the frontier of human expert knowledge.

N/Avs6.9%

Terminal-Bench (Agentic Coding & Terminal Use)

Autonomous multi-step tasks executed inside a real command-line terminal environment.

36%vs26.5%

SciCode (Scientific Computing)

Research-grade coding problems drawn from real scientific and numerical workloads.

N/Avs27.2%

LiveCodeBench (Competitive Coding)

Contamination-free competitive programming problems collected continuously over time.

N/Avs45%

AIME (Advanced Math Competition)

American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.

66%vs54%

Long-Context Reasoning

Accuracy when reasoning over very large inputs that fill the model context window.

80%vs75%

Generation Speed (Throughput)

Tokens emitted per second during active generation streaming.

65 tok/s vs82 tok/s

Latence et Temps de Réponse

Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.

Time to First Token (TTFT)Lower is better

Command R+0.58s

Jamba 1.5 Large0.49s

Est. End-to-End Response (500 tokens)TTFT + generation time

Command R+8.27s

Jamba 1.5 Large6.59s

Simulateur Interactif de Coût de Tokens

Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.

Daily Input Tokens100K / day

10K500K1M

Daily Output Tokens30K / day

5K150K300K

Prompt Cache Hit Ratio50% cached

0% (Cold)50%90% (Warm)

Command R+ Monthly API Bill

$13.88 / month

$2.5/1M in · $10/1M out

Jamba 1.5 Large Monthly API Bill

$10.95 / month

$2/1M in · $8/1M out

Jamba 1.5 Large saves approximately $2.93 / month (21%) under this workload.1.3x Savings

Command R+ · Strengths & Key Advantages

Fenêtre de contexte de 128K et capacité de sortie maximale de 8K tokens (SWE-bench Verified 41.5% · GPQA Diamond 56.5%)
Débit rapide de 65 tokens/seconde avec une latence au premier token (TTFT) de 580 ms
Poids ouverts (104B) permettant un déploiement sur site ou cloud privé via vLLM, SGLang ou Ollama

Considerations & Trade-offs

Nécessite des serveurs GPU dotés de suffisamment de mémoire VRAM pour l’inférence locale à pleine précision
Pour les charges à très fort volume, l’activation du cache de prompts et de l’API Batch est recommandée

Jamba 1.5 Large · Strengths & Key Advantages

Fenêtre de contexte de 256K et capacité de sortie maximale de 4K tokens (SWE-bench Verified 41.2% · GPQA Diamond 51%)
Débit rapide de 82 tokens/seconde avec une latence au premier token (TTFT) de 490 ms
Poids ouverts (398B (94B )) permettant un déploiement sur site ou cloud privé via vLLM, SGLang ou Ollama

Considerations & Trade-offs

Nécessite des serveurs GPU dotés de suffisamment de mémoire VRAM pour l’inférence locale à pleine précision
Pour les charges à très fort volume, l’activation du cache de prompts et de l’API Batch est recommandée

Token Use & Task Economics

Estimated cost and token consumption to complete one representative agentic task.

Metric	Command R+	Jamba 1.5 Large
Cost per Task Estimated USD to finish one task	$0.65	$0.48
Output Tokens / Task Tokens generated per task	35K	25K
Reasoning Tokens / Task Thinking tokens burned per task	0K	0K

Spécifications Techniques

Architecture, release timeline, capabilities, and modalities.

Caractéristique	Command R+	Jamba 1.5 Large
Official API Model ID (SDK)	command-r-plus	jamba-1-5-large
API Protocol	OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI	OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Release Date	2024-08	2024-08
Knowledge Cutoff	June 2024	March 2024
Architecture	Enterprise-Grade Dense Transformer	Hybrid SSM-Transformer (Mamba + Transformer MoE)
Parameters	104B	398B (94B active)
Enterprise Rate Limits (RPM / TPM)	Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud	Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Tier (>128K/200K)	Flat rate ($2.5/1M in) across full 128K window	Flat rate ($2/1M in) across full 256K window
Prompt Cache Policy & TTL	Cached input at $0.75/1M tokens	Cached input at $0.5/1M tokens
Computer Use / GUI Agent	API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)	API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling	Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema	Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Sandbox	Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools	Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Official Fine-Tuning Support	Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)	Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Token Billing	Text BPE (~4 chars/token)	Text BPE (~4 chars/token)
Quantization & Min GPU VRAM	BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 64 GB VRAM (4-bit Quantized) · 224 GB VRAM (Native BF16)	BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 247 GB VRAM (4-bit Quantized) · 856 GB VRAM (Native BF16)
Safety & Frontier Classification	Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)	Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (ZDR/HIPAA/SOC2)	100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control	100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Input Modalities	text	text
Output Modalities	text	text

Command R+ vs Jamba 1.5 Large: Réponses Rapides (FAQ)

Which is more intelligent, Command R+ or Jamba 1.5 Large?

Command R+ is more intelligent. It scores 48 compared with 42 on the composite Intelligence Index.

Which model is faster?

Jamba 1.5 Large is faster, generating 82 tokens per second compared with 65 tokens per second.

Which model is cheaper to run?

Jamba 1.5 Large is cheaper at $1.55 per 1M tokens blended, compared with $2.02 (7:2:1 cache:input:output ratio).

Which model has lower latency?

Jamba 1.5 Large has lower latency, with a time to first token of 0.49s compared with 0.58s.

Which model has a larger context window?

Jamba 1.5 Large has a larger context window, supporting 256K tokens compared with 128K tokens.

Verdict

Command R+ (Conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, l’intégration RAG et les pipelines de production évolutifs.) et Jamba 1.5 Large (Conçu pour l’auto-hébergement sur infrastructure privée, le fine-tuning et la souveraineté des données, l’intégration RAG et les pipelines de production évolutifs.) répondent à des besoins complémentaires : Command R+ domine sur les benchmarks de raisonnement et de programmation, Jamba 1.5 Large assure un débit supérieur et Jamba 1.5 Large offre le meilleur rapport coût-efficacité en production.

Questions fréquentes

Quel modèle choisir pour le code et le raisonnement, Command R+ ou Jamba 1.5 Large ?+

Sur l’indice d’intelligence composite et les tests de code, Command R+ prend l’avantage. Consultez les scores SWE-bench et GPQA ci-dessus pour plus de détails.

Quelle est la différence de prix API entre Command R+ et Jamba 1.5 Large ?+

Command R+ est facturé $2.50 / $10.00 par million de tokens (entrée/sortie) contre $2.00 / $8.00 pour Jamba 1.5 Large. En coût pondéré, Jamba 1.5 Large est plus économique.

Quel modèle offre la plus grande fenêtre de contexte et la meilleure vitesse ?+

Command R+ prend en charge 128K tokens contre 256K tokens pour Jamba 1.5 Large. Côté vitesse de génération, Jamba 1.5 Large est le plus rapide.

AI Terminology & Guide

Explore Glossary →

Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.

Tokens & Pricing Context Window AI Benchmarks Reasoning Models Tool Calling Model Context Protocol (MCP)

Command R+ vs Jamba 1.5 Large

Changez et Comparez les Modèles

Command R+

Jamba 1.5 Large

Qui gagne où ?

Scores de Benchmarks Vérifiés

Latence et Temps de Réponse

Simulateur Interactif de Coût de Tokens

Command R+ · Strengths & Key Advantages

Considerations & Trade-offs

Jamba 1.5 Large · Strengths & Key Advantages

Considerations & Trade-offs

Token Use & Task Economics

Spécifications Techniques

Command R+ vs Jamba 1.5 Large: Réponses Rapides (FAQ)

Verdict

Questions fréquentes

Related reading