Part of Best LLM for AI Agents
Best LLM for Goose
Claude Opus 5.5 ranks first for Goose as of October 22, 2026.[1][2][3][4] Leads both Terminal-Bench 4.0 and LMArena's agentic arena, scoring 64.85% on reproducible terminal tasks and ranking #1 with a 20.9 score on human preference for tool-use. Claude Sonnet 5.5 is the next-ranked alternative. Strong second-place showing on Terminal-Bench 4.0 at 61.82%, though its LMArena agentic rank drops to #5, suggesting solid terminal skills with more variable multi-step performance.
- Best open-weight pick: GLM 5.3 (#6)
- Compare Claude Opus 5.5 vs Claude Sonnet 5.5 →
About this recommendation
- Updated
- Evidence through
- Sources
- 11
- Revision
- v101
Decision audit
Why this result
Inspect the inputs and the computed order behind the recommendation.
Models screened
24
live candidates
Evaluation feeds
5
task-weighted
Winner coverage
56%
intended feed weight
Largest provider share
3 of 8
Anthropic
Anthropic: Claude Opus 5.5 leads the measured task comparison with 2 independent evaluation families. Community volume, release age and usage popularity add no ranking points. This category also weights its stated price or context criteria.
Real-world track record is still developing. The recommendation can lead on independent measurements while practitioner reports accumulate.
Sources evaluated
These are the weights used in scoring. Missing measurements are omitted from each model’s average. A feed with no result for any model released in the last 60 days is stale and does not score until it catches up.
| Evaluation feed | Weight | Winner result | Field measured |
|---|---|---|---|
| Berkeley Function Callingstale | 0% | no current result | 0/24 |
| LMArena AgentObserved 2026-10-20 · evaluation date not supplied · max effort | 43% | #1 | 24/24 |
| price weight | 28% | 38/100 | 24/24 |
| Terminal-Bench (4.0)Observed 2026-10-22 · evaluated 2026-10-06 · Claude Code; max effort · 95% interval ±3.11 | 28% | #1 | 14/24 |
| SWE-rebenchstale | 0% | no current result | 0/24 |
Provider concentration
Each exact model is scored separately; provider identity is not a ranking input.
- Anthropic3 models
- OpenAI2 models
- Z.ai2 models
- xAI1 model
Decision table
Every published model is shown in computed order. Practitioner sources are distinct community threads, not the citations repeated in the prose below.
Anthropic · coverage 56%
#1 LMArena Agent · #1 Terminal-Bench
Anthropic · coverage 56%
#2 Terminal-Bench · #5 LMArena Agent
OpenAI · coverage 56%
#3 Terminal-Bench · #4 LMArena Agent
OpenAI · coverage 56%
#2 LMArena Agent · #3 Terminal-Bench
Anthropic · coverage 56%
#3 LMArena Agent · #5 Terminal-Bench
Z.ai · coverage 56%
#9 Terminal-Bench · #25 LMArena Agent
Z.ai · coverage 56%
#12 Terminal-Bench · #31 LMArena Agent
xAI · coverage 56%
#10 Terminal-Bench · #16 LMArena Agent
Task score averages the available, task-weighted measurements. Benchmark positions compare models matched to our catalog. Models measured by at least two independent evaluator families are considered first. Missing tests, practitioner report counts, popularity and release age add no points. Coverage describes evidence breadth, not a probability of correctness. Scores within two points are shown as close under this policy; this is not a statistical confidence interval. When the leading scores are that close, the model measured by more evaluator families ranks first.
- 01
Claude Opus 5.5Anthropic · $4 in / $20 out per M tokens · 1M context
Leads both Terminal-Bench 4.0 and LMArena's agentic arena, scoring 64.85% on reproducible terminal tasks and ranking #1 with a 20.9 score on human preference for tool-use.
Best when: Use for complex repository automation requiring precise multi-step terminal execution, as it tops Terminal-Bench 4.0 at 64.85% with Claude Code.More tips
- Deploy when human preference for agentic tool-use matters most, given its #1 rank (score 20.9) on LMArena's agentic arena.
No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 02
Claude Sonnet 5.5Anthropic · $2 in / $10 out per M tokens · 1M context
Strong second-place showing on Terminal-Bench 4.0 at 61.82%, though its LMArena agentic rank drops to #5, suggesting solid terminal skills with more variable multi-step performance.
Best when: Choose for terminal-heavy workflows where near-top performance suffices, scoring 61.82% on Terminal-Bench 4.0 with Claude Code.Watch out for
- Expect less consistent human preference on open-ended agentic tasks, ranking #5 (score 12.7) versus the leader's 20.9 on LMArena's agentic arena.
- 03
GPT-6.1 SolOpenAI · $2 in / $10 out per M tokens · 1.1M context
Scores 58.18% on Terminal-Bench 4.0 but ranks lower on LMArena agentic preference at #4, showing capable terminal execution with less favored multi-step behavior.
Best when: Use for terminal automation where Codex integration is preferred, achieving 58.18% on Terminal-Bench 4.0.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 04
GPT-6 AstraOpenAI · $10 in / $50 out per M tokens · 1.1M context
Matches Terminal-Bench scores with GPT-6.1 Sol at 58.18% but achieves higher LMArena agentic preference at #2, indicating stronger relative appeal for multi-step tool use.
Best when: Prioritize when LMArena human preference rankings guide your selection, as it places #2 (score 14.7) on the agentic arena.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 05
Claude Fable 5.1Anthropic · $10 in / $50 out per M tokens · 1M context
Ranks #3 on LMArena's agentic arena with score 14.2 while placing #5 on Terminal-Bench 4.0 at 57.88%, showing balanced but not leading performance in both evaluations.
Best when: Select for multi-step tool-use workflows where LMArena preference matters, ranking #3 (score 14.2) on the agentic arena.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 06
GLM 5.3Z.ai · $0.079 in / $1.40 out per M tokens · 1.0M context · open-weight
Best open-weight Terminal-Bench result at 41.82% (#9) with Claude Code, though LMArena agentic preference is weak at #25, indicating open-weight tradeoffs for terminal versus open-ended tasks.
Best when: Select as the open-weight option for terminal automation, scoring 41.82% on Terminal-Bench 4.0 with Claude Code, the highest open-weight result in that evaluation.Watch out for
- Expect poor human preference on agentic tasks, ranking #25 (score 1.4) on LMArena's agentic arena.
- 07
GLM 5.3 FlashZ.ai · $0.006 in / $0.19 out per M tokens · 1.0M context · open-weight
GLM 5.3 Flash scores 35.76% ± 3.54 (95% interval) on Terminal-Bench 4.0 (#12 of 23) at none reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.
Best when: Its strongest result for this task is on Terminal-Bench, which measures completing difficult repository and terminal tasks through an agent harness.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
- 08
Grok 4.7xAI · $2 in / $6 out per M tokens · 500K context
Mid-tier Terminal-Bench performance at 37.58% (#10) with stronger relative standing on LMArena agentic arena at #16, suggesting Grok Build integration affects terminal scoring.
Best when: Evaluate if your deployment uses Grok Build, which achieved 37.58% on Terminal-Bench 4.0 at xhigh reasoning effort.No practitioner reports are linked yet, so no cautions are listed. Absence of reports is not evidence of reliability.
Frequently asked
- What is the best model for Goose?
- Claude Opus 5.5 ranks first as of October 22, 2026. Leads both Terminal-Bench 4.0 and LMArena's agentic arena, scoring 64.85% on reproducible terminal tasks and ranking #1 with a 20.9 score on human preference for tool-use.[1][2]
- What is the best alternative to Claude Opus 5.5?
- Claude Sonnet 5.5 ranks second. Strong second-place showing on Terminal-Bench 4.0 at 61.82%, though its LMArena agentic rank drops to #5, suggesting solid terminal skills with more variable multi-step performance.[3][4]
- Which open-weight model ranks highest for Goose?
- GLM 5.3 is the highest-ranked open-weight model, at #6. Best open-weight Terminal-Bench result at 41.82% (#9) with Claude Code, though LMArena agentic preference is weak at #25, indicating open-weight tradeoffs for terminal versus open-ended tasks.[5][6]
Sources
- 1
“Within the 23 catalog models matched to this evaluation: Scores 64.85% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#1 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026 - 2
“Within the 48 catalog models matched to this evaluation: Ranks #1 of 48 on LMArena's agentic arena (score 20.9), measuring tool-use and multi-step task performance from human preference.”
LMArena agentic arena · Benchmark · Oct 20, 2026 - 3
“Within the 23 catalog models matched to this evaluation: Scores 61.82% ± 2.94 (95% interval) on Terminal-Bench 4.0 (#2 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026 - 4
“Within the 48 catalog models matched to this evaluation: Ranks #5 of 48 on LMArena's agentic arena (score 12.7), measuring tool-use and multi-step task performance from human preference.”
LMArena agentic arena · Benchmark · Oct 20, 2026 - 5
“Within the 23 catalog models matched to this evaluation: Scores 41.82% ± 3.23 (95% interval) on Terminal-Bench 4.0 (#9 of 23) at max reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026 - 6
“Within the 48 catalog models matched to this evaluation: Ranks #25 of 48 on LMArena's agentic arena (score 1.4), measuring tool-use and multi-step task performance from human preference.”
LMArena agentic arena · Benchmark · Oct 20, 2026 - 7
“Within the 23 catalog models matched to this evaluation: Scores 58.18% ± 3.11 (95% interval) on Terminal-Bench 4.0 (#3 of 23) at max reasoning effort, using Codex, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026 - 8
“Within the 48 catalog models matched to this evaluation: Ranks #2 of 48 on LMArena's agentic arena (score 14.7), measuring tool-use and multi-step task performance from human preference.”
LMArena agentic arena · Benchmark · Oct 20, 2026 - 9
“Within the 48 catalog models matched to this evaluation: Ranks #3 of 48 on LMArena's agentic arena (score 14.2), measuring tool-use and multi-step task performance from human preference.”
LMArena agentic arena · Benchmark · Oct 20, 2026 - 10
“Within the 23 catalog models matched to this evaluation: Scores 35.76% ± 3.54 (95% interval) on Terminal-Bench 4.0 (#12 of 23) at none reasoning effort, using Claude Code, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026 - 11
“Within the 23 catalog models matched to this evaluation: Scores 37.58% ± 3.54 (95% interval) on Terminal-Bench 4.0 (#10 of 23) at xhigh reasoning effort, using Grok Build, measuring a model-and-agent configuration on reproducible terminal tasks.”
Terminal-Bench · Benchmark · Oct 22, 2026
Rankings synthesized from community evidence and open benchmarks. See methodology. Not driven by vendor marketing.