Scale Labs SWE Atlas - Test Writing (SWE Atlas - Test Writing)
We show this table for reference; we do not rank on it.
A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.
Scale score on SWE Atlas - Test Writing — November 12, 2026 snapshot
We mirror the published scale score view for SWE Atlas - Test Writing. Fable 5.1 leads the public snapshot at 78.9%, followed by Fable 5.2 (77.8%) and Gemini 4 Argon (77.8%). We do not use these results to rank models overall.
Fable 5.1
Anthropic
SWE Atlas - Test Writing
Fable 5.2
Anthropic
SWE Atlas - Test Writing
Gemini 4 Argon
SWE Atlas - Test Writing
28 modelsCodingCurrentDisplay onlyUpdated November 12, 2026 snapshot
Scale score table (28 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Fable 5.1AnthropicSWE Atlas - Test Writing | 78.9% | Not reported | Unknown |
| 2 | Fable 5.2AnthropicSWE Atlas - Test Writing | 77.8% | Not reported | Unknown |
| 3 | Gemini 4 ArgonGoogleSWE Atlas - Test Writing | 77.8% | Not reported | Closed |
| 4 | Opus 5.5AnthropicSWE Atlas - Test Writing | 77.8% | Not reported | Unknown |
| 5 | Gemini 4 CarbonGoogleSWE Atlas - Test Writing | 76.7% | Not reported | Closed |
| 6 | Gemini 3.8 FlashGoogleSWE Atlas - Test Writing | 71.1% | Not reported | Closed |
| 7 | Sonnet 5.5AnthropicSWE Atlas - Test Writing | 67.8% | Not reported | Unknown |
| 8 | GPT-6 AstraOpenAISWE Atlas - Test Writing | 66.7% | Not reported | Closed |
| 9 | GPT-6.1 SolOpenAISWE Atlas - Test Writing | 66.7% | Not reported | Closed |
| 10 | Grok 4.7xAISWE Atlas - Test Writing | 64.4% | Not reported | Closed |
| 11 | GPT-6.1 TerraOpenAISWE Atlas - Test Writing | 63.3% | Not reported | Closed |
| 12 | Haiku 5.5AnthropicSWE Atlas - Test Writing | 63.3% | Not reported | Unknown |
| 13 | Kimi K3Moonshot AISWE Atlas - Test Writing | 63.3% | Not reported | Open |
| 14 | DeepSeek V4.1 Flash 1017DeepSeekSWE Atlas - Test Writing | 61.1% | Not reported | Open |
| 15 | Muse Wonder 1.0MetaSWE Atlas - Test Writing | 61.1% | Not reported | Unknown |
| 16 | Kimi K3.1 ProMoonshot AISWE Atlas - Test Writing | 58.9% | Not reported | Open |
| 17 | Qwen 3.8 MaxAlibabaSWE Atlas - Test Writing | 58.9% | Not reported | Unknown |
| 18 | Inkling 2 SmallThinking Machines LabSWE Atlas - Test Writing | 58.1% | Not reported | Closed |
| 19 | Muse Ember 1.0MetaSWE Atlas - Test Writing | 56.7% | Not reported | Unknown |
| 20 | GLM-5.3Z.AISWE Atlas - Test Writing | 55.6% | Not reported | Open |
| 21 | GPT-6 LunaOpenAISWE Atlas - Test Writing | 54.4% | Not reported | Closed |
| 22 | GLM-5.3-FlashZ.AISWE Atlas - Test Writing | 53.3% | Not reported | Open |
| 23 | Muse Spark OpenMetaSWE Atlas - Test Writing | 41.1% | Not reported | Open |
| 24 | MiniMax M3MiniMaxSWE Atlas - Test Writing | 40% | Not reported | Open |
| 25 | Mistral Large 4MistralSWE Atlas - Test Writing | 40% | Not reported | Open |
| 26 | Nemotron 3.5 Super VLNvidiaSWE Atlas - Test Writing | 27.8% | Not reported | Unknown |
| 27 | Nemotron 3 UltraNVIDIASWE Atlas - Test Writing | 26.7% | Not reported | Open |
| 28 | GPT-OSS 120BOpenAISWE Atlas - Test Writing | 14.4% | Not reported | Open |
How to read this leaderboard
Compare the published configurations as complete evaluation systems. The source can combine a base model, agent scaffold, tools, budget, and inference setting in each result.
Operator receipt: 28 sourced rows are currently displayable on this page; the leading published row is Fable 5.1 at 78.9%.
Honest limit: This Scale table is display-only context, not benchmark provenance or a weighted model-only comparison.
How BenchLM shows SWE Atlas - Test Writing
BenchLM mirrors 28 published rows from Scale Labs’ public SWE Atlas - Test Writing leaderboard, captured on November 12, 2026 snapshot.
The table is display only. It is useful context for a published agent or model configuration, but it does not enter BenchLM’s overall or category rankings.
Snapshot
The published SWE Atlas - Test Writing snapshot places Fable 5.1 first at 78.9%. The third row is 1.1 points behind. The broader top-10 range is 14.5 points, so the table still separates the published systems.
28 models have been evaluated on SWE Atlas - Test Writing. The benchmark falls in the Coding category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. SWE Atlas - Test Writing is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About SWE Atlas - Test Writing
Year
2026
Tasks
28 published rows
Format
Published Scale leaderboard score
Difficulty
External agent and model evaluation
BenchLM mirrors 28 published rows from the SWE Atlas - Test Writing public table captured on November 12, 2026 snapshot.
Freshness and provenance
Version
SWE Atlas - Test Writing 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does SWE Atlas - Test Writing measure?
A Scale Labs public leaderboard mirrored as display-only reference data. It does not affect BenchLM rankings.
Which model leads the published SWE Atlas - Test Writing snapshot?
Fable 5.1 currently leads the published SWE Atlas - Test Writing snapshot with 78.9% scale score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on SWE Atlas - Test Writing?
The November 12, 2026 snapshot snapshot contains 28 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.