UAB
Home/Find
Find

Describe the job.

Set filters, get ranked options with verified scores and source dates attached.
Recommendation · Research assistant

Best evidence-backed choice for Research assistant with all public sources: claude-opus-5-high.

claude-opus-5-highAnthropic · mid
Verified & stable

The main warning is thinner evidence on Long context.

Direct sources
16
Coverage
60%
Data version
Oct 7, 2026
Evidence behind the call
Data version Oct 7, 202616 direct source linksNo excluded sourcesAll public sources
What the data can support5 ready, 1 partial, 1 missing for the current task result.
Minimum source requirementenough direct data · enough direct data · enough direct data · enough direct data
Cost / latencyLatency is unavailable in the current verified source data.
Best pickclaude-opus-5-high
Runner-upClaude Opus 4.8
Coverage60% visible · 60% checked
PresetResearch assistant
SourcesAll public sources
Latest strong source dataOct 7, 2026
Where sources differ4 source rows behind this answer
1
claude-opus-5-highArena · Document Arena · No Style Control · 1,516.266 · #1 · 100pctl
used for answer
2
claude-opus-5-highArena · Text Arena · Math · 1,520.666 · #3 · 99pctl
used for answer
3
claude-opus-5-highArena · Text Arena · Math · No Style Control · 1,530.609 · #3 · 99pctl
used for answer
4
claude-opus-5-highArtificial Analysis · GPQA · 93.737 · #12 · 98pctl
used for answer
Ranked options

Direct matches first, then weaker or missing-data cases

Direct matches stay strict; strong models with indirect data still surface below. Open a row for its scores, source links, and caveats.

Primary group · Direct-match leaders
#1claude-opus-5-highAnthropic · mid93.260% visible
enough direct data · recent · strong · clearmid-priced price band from registry metadataLatency is unavailable in the current verified source data.
Verified and stable14.9% score spread · 79% recent data · exact alias
Fit score93.2
Strongest source datareasoning math science · document understanding

claude-opus-5-high is strongest on Reasoning / math / science and Document understanding for this preset.

  • Last updated: Latest visible source row is 42 days old.
  • Where sources differ: 15-point cross-domain spread; warning threshold is 30.
  • Data checks: No open review item was matched to this recommendation.

The main warning is thinner evidence on Long context.

Verified rows
8
Hand-checked rows
0
Copied rows
0
Backfilled rows
0
Headline lane
Oct 7, 2026
Background data
No extra context
Formula recommendation-fit-v2.0.0.
Measured by
public third-party sources
Source basis
exact alias
Compared fairly because
same test setup, version groups, source-balanced before averaging
Open model
Open compare
#2Claude Opus 4.8Anthropic · frontier89.380% visible
enough direct data · recent · strong · clearfrontier-priced price band from registry metadataLatency is unavailable in the current verified source data.
Verified but aging10.9% score spread · 65% recent data · exact alias
Fit score89.3
Strongest source datareasoning math science · long context

Claude Opus 4.8 is strongest on Reasoning / math / science and Long context for this preset.

  • Last updated: Latest visible source row is 42 days old.
  • Where sources differ: 11-point cross-domain spread; warning threshold is 30.
  • Data checks: No open review item was matched to this recommendation.

The verified evidence is decent, but too much of it is aging to treat this as a clean current winner.

Verified rows
16
Hand-checked rows
0
Copied rows
0
Backfilled rows
0
Headline lane
Oct 7, 2026
Background data
No extra context
Formula recommendation-fit-v2.0.0.
Measured by
public third-party sources
Source basis
exact alias
Compared fairly because
same test setup, version groups, source-balanced before averaging
Open model
Open compare
#3Claude Opus 4.7Anthropic · frontier88.880% visible
enough direct data · recent · strong · clearfrontier-priced price band from registry metadataLatency is unavailable in the current verified source data.
Verified but aging8.9% score spread · 65% recent data · exact alias
Fit score88.8
Strongest source datareasoning math science · document understanding

Claude Opus 4.7 is strongest on Reasoning / math / science and Document understanding for this preset.

  • Last updated: Latest visible source row is 47 days old.
  • Where sources differ: 9-point cross-domain spread; warning threshold is 30.
  • Data checks: No open review item was matched to this recommendation.

The verified evidence is decent, but too much of it is aging to treat this as a clean current winner.

Fallback benchmark identity is visible for context but excluded from default ranking.

Verified rows
16
Hand-checked rows
0
Copied rows
0
Backfilled rows
0
Headline lane
Oct 7, 2026
Background data
No extra context
Formula recommendation-fit-v2.0.0.
Measured by
public third-party sources
Source basis
exact alias
Compared fairly because
same test setup, version groups, source-balanced before averaging
Open model
Open compare
#4DeepSeek V4 Pro 0424 (Max)DeepSeek · mid87.260% visible
enough direct data · recent · strong · clearmid-priced price band from registry metadataLatency is unavailable in the current verified source data.
Verified and stable20.4% score spread · 100% recent data · exact alias
Fit score87.2
Strongest source datasearch tool use · reasoning math science

DeepSeek V4 Pro 0424 (Max) is strongest on Search / tool use and Reasoning / math / science for this preset.

  • Last updated: Latest visible source row is 42 days old.
  • Where sources differ: 20-point cross-domain spread; warning threshold is 30.
  • Data checks: No open review item was matched to this recommendation.

The main warning is thinner evidence on Long context.

Verified rows
5
Hand-checked rows
0
Copied rows
0
Backfilled rows
0
Headline lane
Oct 7, 2026
Background data
No extra context
Formula recommendation-fit-v2.0.0.
Measured by
public third-party sources
Source basis
exact alias
Compared fairly because
same test setup, version groups, source-balanced before averaging
Open model
Open compare
#5DeepSeek V4 Flash 0420 (Max)DeepSeek · mid85.760% visible
Source status unavailablemid price bandLatency unavailable
Verified and stable19.5% score spread · 100% recent data · exact alias
Fit score85.7
Strongest source datasearch tool use · reasoning math science

DeepSeek V4 Flash 0420 (Max) is strongest on Search / tool use and Reasoning / math / science for this preset.

The main warning is thinner evidence on Long context.

Verified rows
5
Hand-checked rows
0
Copied rows
0
Backfilled rows
0
Headline lane
Oct 7, 2026
Background data
No extra context
Formula recommendation-fit-v2.0.0.

No source link clears the minimum source requirement.

Measured by
public third-party sources
Source basis
exact alias
Compared fairly because
same test setup, version groups, source-balanced before averaging
Open model
Open compare
Evidence & limits

Read the argument before you commit

Why this is the top optiontop reasons behind the current answer
  • claude-opus-5-high leads this preset with a 93.2 weighted fit score.
  • Its strongest visible evidence comes from Reasoning / math / science and Document understanding.
  • Coverage sits at 60%, with 60% backed by verified runtime or manual verification.
What to pressure testwhere the current answer is still fragile
  • Runner-up edge · Claude Opus 4.8: Claude Opus 4.8 is strongest on Reasoning / math / science and Long context for this preset.
  • Evidence risk: The main warning is thinner evidence on Long context.
What would flip the answerthe assumptions the result rests on
  • If you tighten benchmark spread: Claude Opus 4.8 gains ground because its visible benchmark evidence is steadier.
  • If you tighten recency: claude-opus-5-high remains viable because the visible evidence is still fairly fresh.
  • If you require open-weight: No open-weight model currently clears the same evidence floor.
  • If cost and speed matter more: claude-opus-5-high
Why this is not a clean winlimitations to keep in mind
  • The main warning is thinner evidence on Long context.
  • Claude Opus 4.8 remains close enough that a different scoring recipe can still flip the public answer.
Source links6 rows behind this answer
  • Arena · Document Arena · No Style Control · 1,516.266 · #1 · 100pctl
  • Arena · Text Arena · Math · 1,520.666 · #3 · 99pctl
  • Arena · Text Arena · Math · No Style Control · 1,530.609 · #3 · 99pctl
  • Artificial Analysis · GPQA · 93.737 · #12 · 98pctl
  • Vals AI · MortgageTax · 69.912 · #5 · 95pctl
  • Artificial Analysis · Humanity's Last Exam · 48.656 · #29 · 95pctl
Data limitswhere the public data is thin
  • cost: partial · Only registry price bands are ready; exact price calculations are not shown.
  • latency: missing · Latency is not available in the current verified shortlist data.
Not chosen6 well-known models left off

GPT-5.6 Sol

Closest option

  • Missing benchmark coverage in Embeddings / retrieval.
  • GPT-5.6 Sol has direct evidence on part of this preset, but not enough to clear the exact-match floor.
Open model

GPT-5.4

Closest option

  • Missing benchmark coverage in Embeddings / retrieval.
  • GPT-5.4 has direct evidence on part of this preset, but not enough to clear the exact-match floor.
Open model

Gemini 3.5 Flash

Closest option

  • Missing benchmark coverage in Embeddings / retrieval.
  • Gemini 3.5 Flash has direct evidence on part of this preset, but not enough to clear the exact-match floor.
Open model

grok-4.5

Closest option

  • Missing benchmark coverage in Embeddings / retrieval.
  • grok-4.5 has direct evidence on part of this preset, but not enough to clear the exact-match floor.
Open model

GPT-5.6 Terra

Closest option

  • Missing benchmark coverage in Embeddings / retrieval.
  • GPT-5.6 Terra has direct evidence on part of this preset, but not enough to clear the exact-match floor.
Open model

Claude Fable 5

Known current model

  • Current generated catalog does not have enough matching source links for this task preset.
Open model
Needs more source data12 tracked models with thin public data

GPT-5.6 Sol

OpenAI · 80% visible · 80% direct · 0% indirect

GPT-5.6 Sol has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
search tool usereasoning math science

GPT-5.4

OpenAI · 80% visible · 80% direct · 0% indirect

GPT-5.4 has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencedocument understanding

Gemini 3.5 Flash

Google · 80% visible · 80% direct · 0% indirect

Gemini 3.5 Flash has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencedocument understanding

grok-4.5

xAI · 80% visible · 80% direct · 0% indirect

grok-4.5 has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencelong context

GPT-5.6 Terra

OpenAI · 80% visible · 80% direct · 0% indirect

GPT-5.6 Terra has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencelong context

Grok 4.3

xAI · 80% visible · 80% direct · 0% indirect

Grok 4.3 has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
long contextreasoning math science

GPT-5.4 mini

OpenAI · 80% visible · 80% direct · 0% indirect

GPT-5.4 mini has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencelong context

GPT-5.4 nano

OpenAI · 80% visible · 80% direct · 0% indirect

GPT-5.4 nano has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencelong context

qwen3.6-plus

Qwen · 80% visible · 80% direct · 0% indirect

qwen3.6-plus has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
search tool usereasoning math science

Gemini 3.1 Pro

Google · 80% visible · 80% direct · 0% indirect

Gemini 3.1 Pro has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencesearch tool use

Gemini 2.5 Pro

Google · 80% visible · 80% direct · 0% indirect

Gemini 2.5 Pro has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencedocument understanding

Gemini 3 Pro Preview

Google · 80% visible · 80% direct · 0% indirect

Gemini 3 Pro Preview has direct evidence on part of this preset, but not enough to clear the exact-match floor.

  • Missing benchmark coverage in Embeddings / retrieval.
reasoning math sciencedocument understanding

Shareable claims with evidence

The product should generate public claims worth checking, not just filter state.

Open change report
alert
13 review items still need manual judgment

The product keeps parser and mapping ambiguity visible instead of silently guessing.

Open
models
BridgeBench moved via new benchmark coverage

10 benchmark rows were added, 10 removed, and 0 existing rows changed value or evaluation date. Window: 2026-05-15T16:26:59Z -> 2026-05-15T16:34:46Z.

Open
sources
Scale Labs moved via source updated leaderboard

The saved raw source snapshot changed relative to the previous run. Window: 2026-10-07T13:27:10Z -> 2026-10-07T13:28:01Z.

Open
product
Initial comparison-table release

Added comparison-table homepage, same-test normalization, per-cell source links, source pages, and custom-ranking preview.

Open
models
Methodology contract published

Documented comparability rules, raw-vs-normalized behavior, and why unlike metrics are never averaged by default.

What changed this week

alert
13 review items still need manual judgment

The product keeps parser and mapping ambiguity visible instead of silently guessing.

models
BridgeBench moved via new benchmark coverage

10 benchmark rows were added, 10 removed, and 0 existing rows changed value or evaluation date. Window: 2026-05-15T16:26:59Z -> 2026-05-15T16:34:46Z.

Source-data window: 2026-05-15T16:26:59Z -> 2026-05-15T16:34:46Z

sources
Scale Labs moved via source updated leaderboard

The saved raw source snapshot changed relative to the previous run. Window: 2026-10-07T13:27:10Z -> 2026-10-07T13:28:01Z.

Source-data window: 2026-10-07T13:27:10Z -> 2026-10-07T13:28:01Z

product
Initial comparison-table release

Added comparison-table homepage, same-test normalization, per-cell source links, source pages, and custom-ranking preview.

Source-data window: 2026-04-16

models
Methodology contract published

Documented comparability rules, raw-vs-normalized behavior, and why unlike metrics are never averaged by default.

Source-data window: 2026-04-16

models
Artificial Analysis ID rule adopted

Stable model and creator IDs are now the preferred external identity keys when available.

Source-data window: 2026-04-15

models
BridgeBench parser fallback added

Added alternate selectors for category headers after leaderboard markup drift.

Source-data window: 2026-04-15

disagreement
claude-sonnet-5-5-max-effort is still a split decision

Cross-benchmark spread sits at 100.0 points, which means rankings still depend heavily on which visible benchmark slices you weight most.

Data version

Current snapshot.

Published Oct 7, 2026Model list checked4 stale sources1591 claim warnings9 providers · 1339 tracked modelsPage refreshed Nov 18, 2026

Freshness is calculated at request time. Failed sources retain their last verified rows with a visible age penalty. View live data status.

Quick routes

Jump straight to a page.

Resolve a recommendation into a public reportbest open model for long-context researchResearch assistantOpen page
Send a shortlist into compare modecompare gpt-5, claude opus, gemini proEveryday chatbotOpen page
Open a head-to-head debate pagegpt-5 vs claude opusEveryday chatbotOpen page
Open a source-difference reportbenchmark controversy for livebench codingCoding copilotOpen page
Open the latest public movementwhat changed this weekEveryday chatbotOpen page
Jump straight to an entity pageopen model gpt-5Open-weight shortlistOpen page