Skip to main content

Claude Opus 4.8 vs Step 5 Preview

SpecClaude Opus 4.8Step 5 Preview
Respan Index55.7 (#27)55.4 (#28)
Blended price per 1M$10$1.43
Context window1M1M
Input / output per 1M$5 / $25$1 / $2.7
Max output128K64K
Inputtext, visiontext, vision, video
Released2026-05-282026-09-20

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude Opus 4.8Step 5 Preview
Coding39.4 Claude Opus 4.845.4 Step 5 Preview
Agents64.4 Claude Opus 4.856.3 Step 5 Preview
Reasoning64.8 Claude Opus 4.863.9* Step 5 Preview
Knowledge & language52.5 Claude Opus 4.856.6* Step 5 Preview
Human preference55.2 Claude Opus 4.855.3 Step 5 Preview

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

Claude Opus 4.8 leads on 3 of the 5 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Opus 4.8Step 5 Preview
LMArena Elo14821449
LMArena Vision (LMArena)12861247
LMArena WebDev (LMArena)15551570
LMArena Agent (LMArena)0.0776-0.0515
Terminal-Bench 4.0 (Vals AI)23.2%31.8%

FAQ

Is Claude Opus 4.8 better than Step 5 Preview?

Claude Opus 4.8 scores 55.7 on the Respan Index (#27), ahead of Step 5 Preview at 55.4 (#28). Claude Opus 4.8 leads on 3 of the 5 benchmarks both report.

Which is cheaper, Claude Opus 4.8 or Step 5 Preview?

Claude Opus 4.8 lists at $5 input and $25 output per 1M tokens; Step 5 Preview at $1 and $2.7. Step 5 Preview is 7.0x cheaper per token at list price.

Which has the larger context window?

Both accept 1M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.