Skip to main content
BenchLM
Data

Claude Haiku 5.5 vs GPT-OSS 120B

Updated November 21, 2026. Rank says Claude Haiku 5.5 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Claude Haiku 5.5 has the higher public score, 63.5 versus 37.3, and the 90% score intervals do not overlap. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Anthropic logo

Anthropic

63.5/100

Supported · Public rank #38

90% interval 59.5–67.6

Model B
OpenAI logo

OpenAI

37.3/100

Supported · Public rank #172

90% interval 32.1–42.4

API price per 1M tokens

Claude Haiku 5.5: $0.10 input / $0.50 output

GPT-OSS 120B: No comparable API price

Context window

Claude Haiku 5.5: 1M

GPT-OSS 120B: 128K

Released

Claude Haiku 5.5: October 7, 2026

GPT-OSS 120B: August 5, 2025

Shared results
1
Claude Haiku 5.5 only
26
GPT-OSS 120B only
7
Like-for-like categories
4 / 8
Supported: Claude Haiku 5.5 and GPT-OSS 120BHow the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Coding work

    Code generation, repair, and software-engineering tasks

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 41.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Agentic work

    Tool use, computer use, and multi-step task completion

    Claude Haiku 5.5

    Claude Haiku 5.5 has the higher public agentic point estimate, 68.3 to 30.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

    Confidence: limited
  • Long documents

    Prompts that approach the documented context limit

    Claude Haiku 5.5

    Claude Haiku 5.5 has the larger documented context window.

    Confidence: documented
Show secondary and unsupported calls
  • Chat turn cost

    1K fresh input + 500 output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates
  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. GPT-OSS 120B does not fit this workload in one request. GPT-OSS 120B has no comparable published API token rate.

    Confidence: listed-rates
  • Repository review cost

    50K fresh input + 3K output tokens

    Not enough matched evidence

    A complete comparable API-rate estimate is not available for both models.

    Confidence: listed-rates

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

67.9Claude Haiku 5.541.3GPT-OSS 120B

Like-for-like · BenchAlign v6.0

Claude Haiku 5.5 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

A shared-evidence shape is not available.

BenchLM does not draw a radar or infer missing axes when the matched evidence is too sparse.

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.

Agentic

Like-for-like
Claude Haiku 5.5
68.3
Supported · #25/182
GPT-OSS 120B
30.6
Supported · #168/182
Basis
BenchAlign v6.0 lane · 9 vs 1 public rows
Reading
Claude Haiku 5.5 leads

Coding

Like-for-like
Claude Haiku 5.5
67.9
Supported · #28/180
GPT-OSS 120B
41.3
Supported · #122/180
Basis
BenchAlign v6.0 lane · 7 vs 2 public rows
Reading
Claude Haiku 5.5 leads

Reasoning

Like-for-like
Claude Haiku 5.5
62.6
Supported · #38/161
GPT-OSS 120B
38.2
Supported · #132/161
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Claude Haiku 5.5 leads

Knowledge

Like-for-like
Claude Haiku 5.5
50.2
Supported · #84/158
GPT-OSS 120B
36.8
Supported · #133/158
Basis
BenchAlign v6.0 lane · 1 vs 3 public rows
Reading
Claude Haiku 5.5 leads · intervals overlap

Multilingual

Directional only
Claude Haiku 5.5
56.1
Estimated · #36/88
GPT-OSS 120B
37.3
Estimated · #74/88
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Directional only

Instruction following

Directional only
Claude Haiku 5.5
58.3
Supported · #37/143
GPT-OSS 120B
32.9
Estimated · #134/143
Basis
BenchAlign v6.0 lane · 0 vs 0 public rows
Reading
Directional only

Math

Directional only
Claude Haiku 5.5
62.1
Supported · #29/125
GPT-OSS 120B
35.7
Estimated · #103/125
Basis
BenchAlign v6.0 lane · 2 vs 2 public rows
Reading
Directional only

Multimodal

Not comparable
Claude Haiku 5.5
63.9
Supported · #39/119
GPT-OSS 120B
Not ranked
Basis
BenchAlign v6.0 lane · 4 vs 0 public rows
Reading
Not comparable

Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Claude Haiku 5.5
$0.00035
Fits in one request
GPT-OSS 120B
Self-hosted; infrastructure cost varies
Fits in one request

GPT-OSS 120B has no comparable published API token rate.

Repository review

50K fresh input + 3K output tokens

Claude Haiku 5.5
$0.0065
Fits in one request
GPT-OSS 120B
Self-hosted; infrastructure cost varies
Fits in one request

GPT-OSS 120B has no comparable published API token rate.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Claude Haiku 5.5
$0.009
Fits in one request
GPT-OSS 120B
Self-hosted; infrastructure cost varies
Does not fit in one request
Cached-input rate unavailable

GPT-OSS 120B does not fit this workload in one request. GPT-OSS 120B has no comparable published API token rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.

Claude Haiku 5.5

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • Claude Haiku 5.5 is on the efficiency frontier: no cheaper model scores at least as high.
  • GPT-OSS 120B has no public API price, so it is not plotted.

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See Claude Haiku 5.5 on the full price vs performance chart

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Claude Haiku 5.5

$0.01 per 1M cached input tokens

Claude API pricing

GPT-OSS 120B

No comparable hosted API rate

Reasoning profile

Claude Haiku 5.5

Reasoning

GPT-OSS 120B

Non-Reasoning

Weight access

Claude Haiku 5.5

Proprietary

GPT-OSS 120B

Open Weight

License

Claude Haiku 5.5

Proprietary

GPT-OSS 120B

Open Weight

Release date

Claude Haiku 5.5

2026-10-07

GPT-OSS 120B

2025-08-05

If you already use one of these models

Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
Claude Haiku 5.5 has the higher public score, 63.5 versus 37.3, and the 90% score intervals do not overlap.
Workload cost
A complete comparable API-rate estimate is not available for both models.
Context tradeoff
Claude Haiku 5.5 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Claude Haiku 5.5 or GPT-OSS 120B?

Claude Haiku 5.5 has the higher public score, 63.5 versus 37.3, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Claude Haiku 5.5 or GPT-OSS 120B?

Claude Haiku 5.5 has the higher public coding point estimate, 67.9 to 41.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which is better for agentic tasks, Claude Haiku 5.5 or GPT-OSS 120B?

Claude Haiku 5.5 has the higher public agentic tasks point estimate, 68.3 to 30.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.

Which costs less, Claude Haiku 5.5 or GPT-OSS 120B?

Both models do not have comparable published API token rates, so this page does not name a universal price winner.

Which has the larger context window, Claude Haiku 5.5 or GPT-OSS 120B?

Claude Haiku 5.5 has the larger documented context window: 1M, compared with 128K.

Self-host vs API cost

Estimates at 50,000 req/day · 1000 tokens/req average.

Claude Haiku 5.5
API / mo$450
Self-host / moNot listed
Break-even—
Proprietary model — self-hosting not applicable.
GPT-OSS 120B
API / mo (DeepInfra)$155
Self-host / mo$3,495
Break-evenNot reached at 70% load
Model the full break-even

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence34 rows

Agentic

  • Claude Haiku 5.558.62%
    GPT-OSS 120B21.14%

    Claude Haiku 5.5 leads this result

  • Terminal-Bench 4.1

    Claude Haiku 5.540.00%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Agents' Last Exam (Linux)

    Claude Haiku 5.557.0%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Terminal-Bench 4.0

    Claude Haiku 5.539.20%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • HLE w/ tools

    Claude Haiku 5.557.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • MazeBench

    Claude Haiku 5.51%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Hermes Index

    Claude Haiku 5.537.0%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Hermes Bench

    Claude Haiku 5.571.0%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • OSWorld 2.1 Offline

    Claude Haiku 5.572.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

Coding

  • FrontierCode 1.1 Main

    Claude Haiku 5.546.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Bug Hunt Bench

    Claude Haiku 5.521.5 fixes
    Source
    GPT-OSS 120B—

    Not directly comparable

  • FrontierSWE v2

    Claude Haiku 5.543.8%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • FrontierCode 2.0

    Claude Haiku 5.528.9%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • CursorBench 4.0

    Claude Haiku 5.548.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • VulcanBench Frontier v4

    Claude Haiku 5.592.2%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • CursorBench 4.1

    Claude Haiku 5.548.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • SWE-bench Verified

    Claude Haiku 5.5—
    GPT-OSS 120B62.4%
    Source

    Not directly comparable

  • React Native Evals

    Claude Haiku 5.5—
    GPT-OSS 120B71.6%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-1

    Claude Haiku 5.589.00%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • ARC-AGI-2

    Claude Haiku 5.561.3%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • ARC-AGI-3

    Claude Haiku 5.50.5%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Claude Haiku 5.52.82%
    Source
    GPT-OSS 120B—

    Not directly comparable

Multimodal

  • ParseBench-2

    Claude Haiku 5.571.24%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • PerceptionBench (tools)

    Claude Haiku 5.578.6%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • ParseBench-1

    Claude Haiku 5.556.06%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • Chartography (no tools)

    Claude Haiku 5.546.4%
    Source
    GPT-OSS 120B—

    Not directly comparable

Knowledge

  • HLE w/o tools

    Claude Haiku 5.545.9%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • MMLU

    Claude Haiku 5.5—
    GPT-OSS 120B90%
    Source

    Not directly comparable

  • GPQA

    Claude Haiku 5.5—
    GPT-OSS 120B80.1%
    Source

    Not directly comparable

  • HLE

    Claude Haiku 5.5—
    GPT-OSS 120B14.9%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Claude Haiku 5.575.088%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • FrontierMath v2 (Tier 4)

    Claude Haiku 5.546.341%
    Source
    GPT-OSS 120B—

    Not directly comparable

  • AIME 2024

    Claude Haiku 5.5—
    GPT-OSS 120B95.8%
    Source

    Not directly comparable

  • AIME 2025

    Claude Haiku 5.5—
    GPT-OSS 120B92.5%
    Source

    Not directly comparable

34 public results · 1 shared

Watch Claude Haiku 5.5 vs GPT-OSS 120B

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 21, 2026