Undominated.ai

Model comparison · accepted catalogue facts 2026-09-23

Claude Opus 4.8 vs Claude Opus 5

Claude Opus 5 has an equal-or-higher measured score and an equal-or-lower estimated price. No known model-capability loss from Claude Opus 4.8; endpoint and task checks still apply. The reported score intervals do not overlap; this is not a task-specific success guarantee.

Editorial comparison: Opus migration shortlist: compare exact catalogue versions without assuming tokenizer or endpoint equivalence. Inclusion does not recommend either model.

Claude Opus 4.8

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

1460.8

Balanced effective USD / 1M tokens · lower is better

$10.00/M

Claude Opus 5

LMArena general · Elo · higher is better

Scale starts at 1040 Elo

1504.9

Balanced effective USD / 1M tokens · lower is better

$10.00/M

Compare · model decision

Choose two or three models

Inspect the differences, estimate your workload and keep the evidence. All standard catalogue models are available, including unrated ones.

Catalogue facts
2026-09-23

2 / 3 selected · 0 requirements
Open public comparison link
Public workload and requirements

These settings are included in the share link. The fixed-request scenario and private evaluation data below are excluded.

A ↔ B

Claude Opus 5 has an equal-or-higher measured score and an equal-or-lower estimated price. No known model-capability loss from Claude Opus 4.8; endpoint and task checks still apply. The reported score intervals do not overlap; this is not a task-specific success guarantee.

Estimated blend: 75% input, 25% output; 0% cached input. Base context tier. Prompt length selects the billing tier. An unlisted cache-read rate uses that tier’s full input rate in this blend; missing required input or output rates prevent an estimate. The fixed-request estimate below validates actual context and output limits and requires a published cache-read rate when cache hits are assumed.

What changes between these models

Quality first, then estimated price. LMArena scores are human-preference measurements, not a benchmark of your application. A missing score is unrated.

  • Claude Opus 4.8 · Meets the stated model requirements
  • Claude Opus 5 · Meets the stated model requirements
Material differences and unknown evidence. Deltas compare each model with model A. Unknown facts remain visible.
Measured factA Claude Opus 4.8B Claude Opus 5
LMArena general score (Elo)1,460.81,504.9Δ vs A: +44.1 Elo
Score interval half-width (± Elo)4.164.22Δ vs A: +0.06 Elo
LMArena document score (Elo)1,474.81,516.3Δ vs A: +41.5 Elo
Recorded retirement dateUnknownUnknown
16 shared measured facts
Shared measured facts. Deltas compare each model with model A. Unknown facts remain visible.
Measured factA Claude Opus 4.8B Claude Opus 5
Benchmark reasoning efforthighhigh
Estimated effective USD / 1M tokens$10$10Δ vs A: 0 USD/M
Base input USD / 1M tokens$5$5Δ vs A: 0 USD/M
Base output USD / 1M tokens$25$25Δ vs A: 0 USD/M
Base cached-input USD / 1M tokens$0.5$0.5Δ vs A: 0 USD/M
Context window (tokens)1,000,0001,000,000Δ vs A: 0 tokens
Output limit (tokens)128,000128,000Δ vs A: 0 tokens
Input modalitiestext, image, filetext, image, file
Tool useSupportedSupportedΔ vs A: 0
ReasoningSupportedSupportedΔ vs A: 0
Open weightsNot supportedNot supportedΔ vs A: 0
Recorded licenceproprietaryproprietary
Model providerAnthropicAnthropic
Distinct sellers in the catalogue55Δ vs A: 0
Serving precision differs across offersNot supportedNot supportedΔ vs A: 0
Retirement evidenceNone announced; not a guaranteeNone announced; not a guarantee

Provider counts and precision flags describe catalogue offers. They do not establish the precision, availability, region, tool behaviour or limits of your chosen endpoint. Open each model’s provider table before switching.

Complete price ladders and billing conditions

Claude Opus 4.8

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

Input-token thresholdInputOutputCached input
Base, up to and including first threshold$5$25$0.5

Claude Opus 5

Rates below are USD per 1M tokens. A threshold selects that whole input/output rate pair.

Input-token thresholdInputOutputCached input
Base, up to and including first threshold$5$25$0.5
Migration preflight · compare each candidate with model A

Keeping Claude Opus 4.8 is a valid decision. No pairwise comparison certifies a drop-in replacement.

Claude Opus 4.8 → Claude Opus 5

No known model-capability loss

  • Provider endpoint, serving precision, availability and task success need your own verification. Catalogue model capabilities do not certify an endpoint.
Check alternatives to Claude Opus 4.8

Estimate a fixed request shape

Private to this tab unless you save locally or explicitly export private details. These are estimates, not observed invoices. Cross-model token counts and task success are assumptions.

0.1 extra attempts means 10 extra full attempts per 100 requests. Cache writes, tool charges, taxes and unlisted charges are excluded.

  • Claude Opus 4.8Estimated total: $22.5 1,000 full attempts · base rates
  • Claude Opus 5Estimated total: $22.5 1,000 full attempts · base rates
Prompt and output sensitivity · sampled scenarios

Every point recalculates the entire request shape. Tier-boundary samples include one token below, at and above each threshold. Ordering between samples is not guaranteed. Lowest known cost excludes unknown estimates and is not a replacement recommendation.

Vary input; hold output, requests, cache and retries fixed.
Input tokensClaude Opus 4.8Claude Opus 5Coverage
2,000$22.5Lowest known$22.5Lowest knownAll computed
4,096$32.98Lowest known$32.98Lowest knownAll computed
32,768$176.34Lowest known$176.34Lowest knownAll computed
131,072$667.86Lowest known$667.86Lowest knownAll computed
Vary output; hold input, requests, cache and retries fixed.
Output tokensClaude Opus 4.8Claude Opus 5
128$13.2$13.2
2,048$61.2$61.2
8,192$214.8$214.8

Bring your observed evaluation results

JSON is parsed locally. Prompts, filenames, individual responses and extra fields are not retained. Import only aggregate measurements for selected models. Task/version labels do not establish that two evaluations used the same dataset.

Expected format
[{"model":"provider/exact-model-id","task":"support-answer","version":"rubric-1","attempts":100,"successes":84,"costUsd":2.4,"latencyMs":950}]

Use the exact catalogue ID. Replace the example values with observed measurements. Omit costUsd or latencyMs when they are unknown. No public score is inferred from these observations.

Keep the decision and its evidence

A portable record retains selected facts, complete tier ladders, public requirements and the publication manifest. It also embeds the full permitted public catalogue to verify the input artifact checksum. Files are larger for this reason (up to 2 MB); local storage is limited to 12 records. Team review is local to this browser; there is no hosted collaboration.

Saving is opt-in and includes private review fields. Shared comparison links never include them. Version 1 Check references remain separate and are not overwritten or guessed into this format.

Saved local decisions · 0

No version 2 decision records are stored in this browser.

Questions this page answers

Is Claude Opus 4.8 a better-and-cheaper replacement for Claude Opus 5?

Claude Opus 5 has an equal-or-higher measured score and an equal-or-lower estimated price. No known model-capability loss from Claude Opus 4.8; endpoint and task checks still apply. The reported score intervals do not overlap; this is not a task-specific success guarantee.

What is included in this comparison?

Accepted model capabilities, context and output limits, complete price-tier ladders, independent LMArena measurements and missing evidence. Provider endpoint precision and application success still need verification.

Can I compare a different workload or keep a decision record?

Yes. Change the public workload, prompt length and requirements in the comparison workspace. Fixed-request scenarios, aggregate evaluations and review notes stay local unless explicitly exported.

Evidence & Ask