Anthropic, released Oct 22, 2024
Claude Sonnet 3.5 v2price, context, benchmarks and release details
Provisional: not enough results to rank yet 100% confidence 100 percent, Full confidence, 4 of 6 expected sources in
51.9
SI Score
#101 of 142 ranked models
- Input, per 1M tokens
- not yet reported
- Output, per 1M tokens
- not yet reported
- Context window
- 200Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Max output
- 8.2Kmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - Released
- Oct 22, 2024models.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗
How the score breaks down
Coding (weight 40 percent) 50.9
Math (weight 15 percent) 40.8
Preference (weight 15 percent) 62.0
Reasoning (weight 30 percent) 55.3
Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.
Around it on the leaderboard
- 99 Qwen3 30B A3B 52.6
- 100 GPT OSS 20B 52.5
- 101 Claude Sonnet 3.5 v2 51.9
- 102 Claude Opus 4.1 51.5
- 103 o4-mini 51.2
Benchmark results
6 benchmarks, 8 resultsEach row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.
GPQA Diamondreasoning 55.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jan 27, 2025
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 55.3
Open source ↗ 55.3
MATH Level 5math 56.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jan 27, 2025
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 56.9
Open source ↗ 56.9
OTIS Mock AIME 2024–2025math 8.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025
Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 8.5
Open source ↗ 8.5
Aider Polyglotcoding 51.6%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Jan 17, 2025
Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 51.6
Open source ↗ 51.6
SWE-bench Verifiedcoding 53%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] OpenHandsPublished Oct 29, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗
53.0 3 settings
- Setting 1 46.2%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AutoCodeRover-v2.0Published Nov 8, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 2 51.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] AutoCodeRover-v2.1Published Jan 22, 2025
Retrieved Oct 9, 2026 · factual citation
Open source ↗ - Setting 3 53%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] OpenHandsPublished Oct 29, 2024
Retrieved Oct 9, 2026 · factual citation
Open source ↗
LMArena Textpreference 1297.8 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 8, 2026
Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 62.0
Open source ↗ 62.0
Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.
Details and sources
- Open weights
- Nomodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - License
- not yet reported
- Input modalities
- text, image, pdfmodels.devPublished source fact
Retrieved Oct 9, 2026 · MIT
Open source ↗ - First seen by SuperIndex
- Oct 8, 2026
- Coverage
- 80% of expected source weight
Reported (4)
- Aider polyglotOct 8, 2026
- Epoch AI BenchmarkingOct 8, 2026
- LMArena / ArenaOct 8, 2026
- SWE-bench VerifiedOct 8, 2026
Awaiting (2)
- Official model cards via models.dev5% of weight
- LiveBench15% of weight
Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.