AI Battle > Rankings > SciCode: Output Tokens per Task
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) by Anthropic leads the SciCode: Output Tokens per Task ranking with a score of 646. The ranking covers 20 evaluated eval scicode from a public dataset that AI Battle re-checks daily.
Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 20 entries shown.
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic | 646 | 0.0% |
| 2 | Gemini 3.7 Flash (medium) | 391 | -39.4% | |
| 3 | GPT-5.6 Sol (max) | OpenAI | 381 | -41.0% |
| 4 | Kimi K3 (max) | Kimi | 466 | -27.8% |
| 5 | Grok 4.6 (high) | SpaceXAI | 352 | -45.5% |
| 6 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 867 | 34.3% |
| 7 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 743 | 15.1% |
| 8 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic | 770 | 19.2% |
| 9 | GPT-6 Astra (max) | OpenAI | 400 | -38.1% |
| 10 | Muse Glimmer (high) | Meta | 312 | -51.7% |
| 11 | Gemini 3.5 Flash-Lite | 433 | -33.0% | |
| 12 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 702 | 8.7% |
| 13 | gpt-oss-120b (high) | OpenAI | 1063 | 64.7% |
| 14 | K2 Horizon 375B A23B | MBZUAI Institute of Foundation Models | 353 | -45.4% |
| 15 | Muse Spark 1.1 (xhigh) | Meta | 651 | 0.8% |
| 16 | GPT-5.6 Luna (max) | OpenAI | 419 | -35.1% |
| 17 | Muse Spark 1.3 (xhigh) | Meta | 584 | -9.6% |
| 18 | Muse Spark 1.3 (max) | Meta | 583 | -9.8% |
| 19 | GPT-5.6 Terra (max) | OpenAI | 364 | -43.6% |
| 20 | DeepSeek V4.1 Flash (Reasoning, Max Effort) | DeepSeek | 356 | -44.8% |
Across the 20 numeric entries in this window the median is 450 and the mean is 542, so the typical entry sits 196 below the leader. The window spans 312 to 1063.
10 of 20 entries are at or above the median, and the top three hold 25% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.
9 creators appear in this window; the three most-represented hold 65% of the entries.
| Creator | Entries | Highest value | Top entry |
|---|---|---|---|
| OpenAI | 5 | 1063 | gpt-oss-120b (high) |
| Anthropic | 4 | 867 | Claude Opus 5 (Adaptive Reasoning, Max Effort) |
| Meta | 4 | 651 | Muse Spark 1.1 (xhigh) |
| 2 | 433 | Gemini 3.5 Flash-Lite | |
| NVIDIA | 1 | 743 | Nemotron 3 Ultra 550B A55B (Reasoning) |
| Kimi | 1 | 466 | Kimi K3 (max) |
| DeepSeek | 1 | 356 | DeepSeek V4.1 Flash (Reasoning, Max Effort) |
| MBZUAI Institute of Foundation Models | 1 | 353 | K2 Horizon 375B A23B |
| SpaceXAI | 1 | 352 | Grok 4.6 (high) |
The same models are measured across multiple independent datasets. Aggregating the 20 entries above against every other AI Battle dataset gives this cross-section, computed by AI Battle and published nowhere upstream:
| Model | Datasets | Best placements elsewhere |
|---|---|---|
| Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 22 | #2/20 in AA-Omniscience Index: Token Usage, #2/20 in AA-LCR v1.1: Output Tokens per Task, #2/20 in SciCode: Time per Task |
| Gemini 3.7 Flash (medium) | 4 | #1/20 in SciCode: Time per Task, #4/20 in SciCode: Cost per Task, #4/20 in SciCode: Score |
| GPT-5.6 Sol (max) | 56 | #4/20 in 𝜏³-Banking: Output Tokens per Task, #5/20 in AA-LCR v1.1: Output Tokens per Task, #6/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary |
| Kimi K3 (max) | 60 | #1/20 in Context Window, #1/20 in AA-LCR v1.1: Score, #1/14 in Model Size: Total and Active Parameters |
| Grok 4.6 (high) | 61 | #2/20 in 𝜏³-Banking: Score, #5/20 in AA-Briefcase Elo, #5/20 in AA-Omniscience Index |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 44 | #2/20 in AA-Briefcase Elo, #2/20 in GDPval-AA v2 Leaderboard, #2/20 in AA-Briefcase Elo |
| Nemotron 3 Ultra 550B A55B (Reasoning) | 46 | #1/12 in Artificial Analysis Openness Index: Score, #1/12 in Artificial Analysis Openness Index: Components, #2/20 in 𝜏³-Banking: Time per Task |
| Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | 20 | #2/20 in Humanity's Last Exam: Score, #2/20 in AA-Omniscience Accuracy, #2/20 in AA-Briefcase Rubric Pass Rate by File Type (Normalized) |
| GPT-6 Astra (max) | 51 | #1/19 in MMMU-Pro: Score, #2/20 in AA-Omniscience Index, #2/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary |
| Muse Glimmer (high) | 43 | #1/20 in Output Tokens per Intelligence Index Task, #1/20 in Cost per Intelligence Index Task, #1/20 in Cost per Intelligence Index Task |
| Gemini 3.5 Flash-Lite | 44 | #1/20 in End-to-End Response Time, #1/20 in Output Speed, #1/20 in Time per Intelligence Index Task |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 40 | #2/20 in SciCode: Score, #3/20 in AA-Omniscience Index, #3/20 in AA-Omniscience Index |
| gpt-oss-120b (high) | 39 | #1/20 in Cost to Run Artificial Analysis Intelligence Index, #1/20 in Cost to Run Artificial Analysis Intelligence Index, #1/20 in Humanity's Last Exam: Cost per Task |
| K2 Horizon 375B A23B | 24 | #2/20 in AA-Omniscience Hallucination Rate, #8/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #12/20 in AA-Omniscience Index: Token Usage |
| Muse Spark 1.1 (xhigh) | 3 | #9/20 in SciCode: Score, #11/20 in SciCode: Cost per Task |
| GPT-5.6 Luna (max) | 58 | #1/11 in Cost per Task, #1/11 in Cost per Task, #3/20 in Pricing: Cache Hit, Input, and Output |
| Muse Spark 1.3 (xhigh) | 12 | #3/20 in 𝜏³-Banking: Time per Task, #5/20 in SciCode: Score, #7/20 in GDPval-AA v2 Leaderboard |
| Muse Spark 1.3 (max) | 61 | #3/20 in AA-Briefcase Elo, #3/20 in Output Speed, #3/20 in GDPval-AA v2 Leaderboard |
| GPT-5.6 Terra (max) | 52 | #7/20 in AA-Briefcase Output Tokens per Task, #8/20 in Humanity's Last Exam: Output Tokens per Task, #9/20 in Output Speed |
| DeepSeek V4.1 Flash (Reasoning, Max Effort) | 56 | #3/20 in End-to-End Response Time, #3/20 in Latency: Time To First Answer Token, #2/11 in Cost per Task |
This ranking carries the metrics
answer, reasoning from the
SciCode: Output Tokens per Task dataset in the tab::eval-scicode family. Units and the
direction of "better" are not declared by the source dataset, so AI Battle does not invent
them: values are shown exactly as published, and the ordering is the source dataset's own.
Rebuilt on from the
public dataset SciCode: Output Tokens per Task (family tab::eval-scicode).
The source lists 20 entries and all 20 are shown here. AI Battle requests
the dataset's rows, keeps the ordering the source publishes, and computes only the statistics
on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file.
Nothing on this page is generated text about the entries — the numbers come from the source.
Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.
Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/eval-scicode-scicode-output-tokens-per-task.json. Free to reuse with attribution to AI Battle and the source dataset.
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) by Anthropic currently leads the SciCode: Output Tokens per Task ranking with a score of 646, the highest value in this dataset across eval scicode. AI Battle aggregates the dataset from its public source and re-checks it daily.
The SciCode: Output Tokens per Task ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released — each ranking page names the dataset it comes from.
The top 3 are: 1. Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) (646), 2. Gemini 3.7 Flash (medium) (391), 3. GPT-5.6 Sol (max) (381).