Claude Code vs. Opencode

Comparación entre Claude Code y Opencode en el Índice de agentes de programación de Artificial Analysis, incluidos resultados de benchmarks, costo, tiempo de ejecución y uso de tokens.

Para más detalles sobre nuestra metodología, consulta nuestra página de metodología.

Explora otras comparaciones
vs

Destacados

Índice de agentes de programación

Artificial Analysis Coding Agent Index v1.4 · Higher is better

Tiempo por tarea

Average agent wall time per task · Lower is better

Costo por tarea

Average API cost per task (USD) · Lower is better

Comparación

Comparación lado a lado de Claude Code y Opencode.

Comparación de agentes de programación

Métrica
Claude Code
Fable 5.1 (max) (with fallback)
Opencode
Gemini 3.8 Flash (high)
Análisis
Harness del agente
Claude Code
Opencode
Modelo representativo
Fable 5.1 (max) (with fallback)
Gemini 3.8 Flash (high)
Índice de agentes de programación
70
61
Claude Code tiene un Índice de agentes de programación más alto que Opencode
DeepSWE
66%
62%
Claude Code tiene una puntuación más alta en DeepSWE que Opencode
Terminal-Bench v2.1
89%
84%
Claude Code tiene una puntuación más alta en Terminal-Bench v2.1 que Opencode
SWE-Atlas-QnA
56%
38%
Claude Code tiene una puntuación más alta en SWE-Atlas-QnA que Opencode
Costo por tarea
$9.18
$2.04
Opencode tiene un costo por tarea más bajo que Claude Code
Tiempo por tarea
24.0m
11.9m
Opencode tiene un tiempo por tarea más bajo que Claude Code
Turnos por tarea
25.4
119.5
Claude Code tiene menos turnos por tarea que Opencode
Uso de tokens por tarea
7.1M
27.8M
Claude Code tiene un uso de tokens por tarea más bajo que Opencode
Tasa de aciertos de caché
90%
88%
Claude Code tiene una tasa de aciertos de caché más alta que Opencode

Variantes de modelo

Variantes de modelo evaluadas para Claude Code y Opencode.

Variantes de modelo

Claude Code
Fable 5.1 (max) (with fallback)
70
66%
89%
56%
$9.18
24.0m
7.1M
Claude Code
Opus 5 (xhigh)
68
60%
89%
55%
$8.17
23.7m
21.6M
Claude Code
Fable 5 (max) (with fallback)
67
66%
87%
49%
$11.69
23.5m
13.9M
Claude Code
Opus 5 (max)
67
63%
89%
49%
$8.94
24.2m
23.7M
Claude Code
Fable 5 (xhigh) (with fallback)
66
65%
87%
46%
$8.53
17.1m
10.3M
Claude Code
Opus 5 (high)
66
61%
87%
49%
$3.92
14.0m
9.9M
Claude Code
Fable 5 (high) (with fallback)
65
64%
89%
42%
$5.97
12.2m
7.1M
Claude Code
Opus 5 (medium)
64
63%
85%
44%
$3.17
12.2m
8M
Claude Code
Fable 5 (medium) (with fallback)
63
64%
87%
39%
$4.74
11.0m
5.7M
Claude Code
Opus 4.8 (max)
62
56%
84%
47%
$7.72
23.1m
17.9M
Claude Code
Qwen3.8 Max
61
52%
84%
48%
$3.23
29.9m
12.5M
Claude Code
Opus 5 (low)
59
57%
82%
39%
$2.30
10.0m
5.3M
Claude Code
Opus 5 (none)
59
44%
82%
52%
$3.53
11.8m
9.2M
Claude Code
Opus 4.8 (xhigh)
59
51%
83%
43%
$5.67
17.8m
13.6M
Claude Code
Fable 5 (low) (with fallback)
59
60%
82%
34%
$3.17
8.2m
3.7M
Claude Code
Opus 4.8 (high)
58
52%
82%
39%
$3.78
12.7m
9.2M
Claude Code
Opus 4.8 (medium)
56
49%
82%
36%
$3.30
12.0m
7.8M
Claude Code
Opus 4.7 (max)
52
40%
78%
37%
$5.92
15.8m
16.1M
Claude Code
Opus 4.8 (low)
49
41%
78%
28%
$2.18
8.6m
5.2M
Claude Code
GLM-5.2
43
29%
72%
29%
$1.91
25.1m
10.8M
Claude Code
Opus 4.7 (medium)
42
27%
77%
23%
$1.80
6.7m
4.6M
Claude Code
Sonnet 4.6 (medium)
39
29%
67%
20%
$2.04
13.8m
8.4M
Claude Code
Qwen3.7 Plus (thinking)
38
19%
72%
24%
$6.30
10.7m
8.8M
Claude Code
GLM-5.1
37
19%
67%
25%
$4.28
19.0m
25.8M
Claude Code
Kimi K2.6
34
17%
69%
16%
$1.22
40.7m
11.7M
Claude Code
DeepSeek V4 Pro (high)
33
9%
70%
20%
$0.25
17.9m
9.9M
Opencode
Gemini 3.8 Flash (high)
61
62%
84%
38%
$2.04
11.9m
27.8M
Opencode
Gemini 3.7 Flash (high)
60
57%
91%
31%
$1.27
8.8m
18.5M
Opencode
Muse Spark 1.2 (xhigh)
59
53%
80%
44%
$1.91
17.7m
16.4M
Opencode
Muse Spark 1.1 (xhigh)
55
54%
77%
33%
$1.44
12.7m
12.3M
Opencode
Opus 4.7 (medium)
51
40%
78%
36%
$2.94
12.5m
7.6M
Opencode
Gemini 3.6 Flash (high)
47
41%
79%
22%
$2.08
10.4m
13M

Rendimiento

Rendimiento en el Índice de agentes de programación de Artificial Analysis.

Índice de agentes de programación de Artificial Analysis

Artificial Analysis Coding Agent Index v1.4 incorporates 3 benchmarks: DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA · Higher is better
Since benchmarking, we have observed a higher rate of content safety filtering on this endpoint.

The Artificial Analysis Coding Agent Index is a composite score built from DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA.

It is useful for quick comparison, but it should be read alongside the per-eval breakdowns. Two agents with similar index values can still have different strengths across repository tasks, terminal workflows, and rubric-based evaluations.

Uso de tokens

Consumo de tokens en el Índice de agentes de programación de Artificial Analysis.

Uso de tokens por tarea

Promedio de tokens de entrada, caché y salida por tarea
Prompt cache hit rates can vary significantly by provider routing, which can materially change effective cost.

Non-cached input tokens sent to the model, including prompts, instructions, tool context, and task context that were not served from prompt cache.

Índice de agentes de programación de Artificial Analysis vs. tokens totales

Índice de agentes de programación de Artificial Analysis vs. promedio de tokens totales por tarea
Most attractive quadrant

Each point represents a coding-agent variant. Farther left means lower average total token usage per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left achieve stronger results with fewer tokens.

Costo

Costo de la API de pago por token en el Índice de agentes de programación de Artificial Analysis, según los precios actuales por token.

Costo por tarea

Average pay-per-token API cost per task (USD) · Lower is better

This chart shows the average pay-per-token API cost per task across the Artificial Analysis Coding Agent Index, spanning DeepSWE, Terminal-Bench v2.1, and SWE-Atlas-QnA.

Where applicable, that cost model includes standard input pricing, discounted cached-input pricing, separate cache-write charges, and output pricing rather than treating all prompt tokens as if they were billed at the same uncached input rate.

It is intended to show pay-per-token API cost, not consumer plan pricing or the full operational cost of deploying the system in production. Infrastructure, engineering, and supervision costs are not the focus of this metric.

Índice de agentes de programación de Artificial Analysis vs. costo por tarea

Índice de agentes de programación de Artificial Analysis vs. promedio del costo de la API de pago por token por tarea (USD)
Most attractive quadrant
Pareto line

Each point represents a coding-agent variant. Farther left means lower average cost per task, while higher on the chart means higher benchmark performance. The most efficient agents sit toward the upper-left: stronger results at lower cost.

Tiempo de ejecución

Tiempo de ejecución activo del agente en el Índice de agentes de programación de Artificial Analysis.

Tiempo por tarea

Average agent wall time per task · Lower is better

This chart uses agent wall time: how long the agent process was actively running on each task.

It does not include environment startup, verifier or judge time, or other harness overhead, so it is a cleaner comparison of how long the agent itself was working.

Índice de agentes de programación de Artificial Analysis vs. tiempo de ejecución

Índice de agentes de programación de Artificial Analysis vs. promedio del tiempo de ejecución del agente por tarea
Most attractive quadrant

Each point represents a coding-agent variant. Farther left means shorter average agent runtime per task, while higher on the chart means higher benchmark performance. Agents toward the upper-left deliver stronger results in less active agent time.