Updated 58 min ago · first seen 11 Sept 2026
model_01M29A5CABC4D1FY1SQRSFF345
- Context
- 200K tokens
- T2 · 58 min ago
Specification
- Status
- deprecated
Source:Artificial AnalysisT2observed 58 min agomedium
- Openness
- proprietary
Source:Artificial AnalysisT2observed 58 min agomedium
- Context window
- 200K tokens
Source:Artificial AnalysisT2observed 58 min agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
4
Source tiers
T24
Freshest observation
58 min ago
Conflicts
None
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 200K tokens
Source:Artificial AnalysisT2observed 58 min agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 7.88 | index | aa_slug=claude-35-sonnet · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 59.9% | accuracy | aa_slug=claude-35-sonnet · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 3.69% | accuracy | aa_slug=claude-35-sonnet · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| SWE-bench (full test split) | 18.13% | resolved | date=2024-06-20 · board=Test · system=SWE-agent · model_tag=claude-3-5-sonnet-20241022 | 20 Jun 2024 | swebench.comT2 |
| SWE-bench Lite | 39% | resolved | date=2025-01-14 · board=Lite · system=Moatless Tools · model_tag=claude-3-5-sonnet-20241022 | 14 Jan 2025 | swebench.comT2 |
| SWE-bench Lite | 47.33% | resolved | date=2024-11-22 · board=Lite · system=devlo · model_tag=claude-3-5-sonnet-20241022 | 22 Nov 2024 | swebench.comT2 |
| SWE-bench Lite | 51.33% | resolved | date=2025-09-11 · board=Lite · system=Isea · model_tag=claude-3.5-sonnet-20241022 | 11 Sept 2025 | swebench.comT2 |
| SWE-bench Lite | 38.33% | resolved | date=2024-11-17 · board=Lite · system=Moatless Tools · model_tag=claude-3-5-sonnet-20241022 | 17 Nov 2024 | swebench.comT2 |
| SWE-bench Lite | 37% | resolved | date=2025-01-04 · board=Lite · system=Patched.Codes Patchwork · model_tag=claude-3-5-sonnet-20241022 | 4 Jan 2025 | swebench.comT2 |
| SWE-bench Lite | 26.67% | resolved | date=2024-06-23 · board=Lite · system=Moatless Tools · model_tag=claude-3-5-sonnet-20241022 | 23 Jun 2024 | swebench.comT2 |
| SWE-bench Lite | 23% | resolved | date=2024-06-20 · board=Lite · system=SWE-agent · model_tag=claude-3-5-sonnet-20241022 | 20 Jun 2024 | swebench.comT2 |
| SWE-bench Lite | 46% | resolved | date=2025-06-19 · board=Lite · system=KGCompass · model_tag=claude-3-5-sonnet-20241022 | 19 Jun 2025 | swebench.comT2 |
| SWE-bench Lite | 44.67% | resolved | date=2024-12-07 · board=Lite · system=Kodu-v1 · model_tag=claude-3-5-sonnet-20241022 | 7 Dec 2024 | swebench.comT2 |
| SWE-bench Lite | 42.67% | resolved | date=2025-05-09 · board=Lite · system=Lingxi · model_tag=claude-3-5-sonnet-20241022 | 9 May 2025 | swebench.comT2 |
| SWE-bench Lite | 41.33% | resolved | date=2024-12-20 · board=Lite · system=PatchKitty-0.9 · model_tag=claude-3-5-sonnet-20241022 | 20 Dec 2024 | swebench.comT2 |
| SWE-bench Lite | 41% | resolved | date=2025-01-13 · board=Lite · system=OrcaLoca + Agentless-1.5 · model_tag=claude-3-5-sonnet-20241022 | 13 Jan 2025 | swebench.comT2 |
| SWE-bench Lite | 40.67% | resolved | date=2024-12-02 · board=Lite · system=Agentless-1.5 · model_tag=claude-3-5-sonnet-20241022 | 2 Dec 2024 | swebench.comT2 |
| SWE-bench Multimodal | 11.41% | resolved | date=2024-10-06 · board=Multimodal · system=SWE-agent Multimodal · model_tag=claude-3-5-sonnet-20241022 | 6 Oct 2024 | swebench.comT2 |
| SWE-bench Multimodal | 5.03% | resolved | date=2024-10-06 · board=Multimodal · system=RAG · model_tag=claude-3-5-sonnet-20241022 | 6 Oct 2024 | swebench.comT2 |
| SWE-bench Multimodal | 25.34% | resolved | date=2025-02-26 · board=Multimodal · system=Agentless Lite · model_tag=claude-3-5-sonnet-20241022 | 26 Feb 2025 | swebench.comT2 |
| SWE-bench Multimodal | 6.19% | resolved | date=2024-10-06 · board=Multimodal · system=Agentless · model_tag=claude-3-5-sonnet-20241022 | 6 Oct 2024 | swebench.comT2 |
| SWE-bench Verified | 54.2% | resolved | date=2024-11-08 · board=Verified · system=devlo · model_tag=claude-3-5-sonnet-20241022 | 8 Nov 2024 | swebench.comT2 |
| SWE-bench Verified | 51.8% | resolved | date=2024-11-25 · board=Verified · system=Engine Labs · model_tag=claude-3-5-sonnet-20241022 | 25 Nov 2024 | swebench.comT2 |
| SWE-bench Verified | 50.8% | resolved | date=2024-12-02 · board=Verified · system=Agentless-1.5 · model_tag=claude-3-5-sonnet-20241022 | 2 Dec 2024 | swebench.comT2 |
| SWE-bench Verified | 49% | resolved | date=2024-10-22 · board=Verified · system=Tools · model_tag=claude-3-5-sonnet-20241022 | 22 Oct 2024 | swebench.comT2 |
| SWE-bench Verified | 63.4% | resolved | date=2025-02-06 · board=Verified · system=AgentScope · model_tag=claude-3-5-sonnet-20241022 | 6 Feb 2025 | swebench.comT2 |
| SWE-bench Verified | 33.6% | resolved | date=2024-06-20 · board=Verified · system=SWE-agent · model_tag=claude-3-5-sonnet-20241022 | 20 Jun 2024 | swebench.comT2 |
| SWE-bench Verified | 39.6% | resolved | date=2024-10-29 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=claude-3-5-sonnet-20241022 | 29 Oct 2024 | swebench.comT2 |
| SWE-bench Verified | 40.6% | resolved | date=2024-10-16 · board=Verified · system=Composio SWEkit · model_tag=claude-3-5-sonnet-20241022 | 16 Oct 2024 | swebench.comT2 |
| SWE-bench Verified | 62.8% | resolved | date=2025-02-28 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=claude-3-5-sonnet-20241022 | 28 Feb 2025 | swebench.comT2 |
| SWE-bench Verified | 60.2% | resolved | date=2025-01-10 · board=Verified · system=Learn-by-interact · model_tag=claude-3-5-sonnet-20241022 | 10 Jan 2025 | swebench.comT2 |
| SWE-bench Verified | 55.4% | resolved | date=2024-12-12 · board=Verified · system=EPAM AI/Run Developer Agent · model_tag=claude-3-5-sonnet-20241022 | 12 Dec 2024 | swebench.comT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
No current prices recorded
Price history
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Statusstatus1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| deprecated | → current | current | Artificial AnalysisT2 | medium | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| proprietary | → current | current | Artificial AnalysisT2 | medium | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 200K tokens | → current | current | Artificial AnalysisT2 | medium | deterministic |
Reasoningreasoning1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Artificial AnalysisT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
claude-35-sonnet scores 5.03% on SWE-bench Multimodal
swebench_leaderboardclaude-35-sonnet scores 6.19% on SWE-bench Multimodal
swebench_leaderboardclaude-35-sonnet scores 11.41% on SWE-bench Multimodal
swebench_leaderboardclaude-35-sonnet scores 25.34% on SWE-bench Multimodal
swebench_leaderboardclaude-35-sonnet scores 23% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 26.67% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 37% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 38.33% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 39% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 40.67% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 41% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 41.33% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 42.67% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 44.67% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 46% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 47.33% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 51.33% on SWE-bench Lite
swebench_leaderboardclaude-35-sonnet scores 33.6% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 39.6% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 40.6% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 49% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 50.8% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 51.8% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 54.2% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 55.4% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 60.2% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 62.8% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 63.4% on SWE-bench Verified
swebench_leaderboardclaude-35-sonnet scores 18.13% on SWE-bench (full test split)
swebench_leaderboard
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| SWE-bench leaderboards | swebench.com/ | leaderboard | T2· Quality secondary | 53 min ago | 1 |
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 58 min ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.